Skip to content

📑 Papers756

ListGrid
What you seeeverything
RecentOldestAddedA–Z
All types1849Papers756Articles568Repos203Threads144
Write-ups82Tools52Talks23Advisories9Other7Courses5
📑 Papers
huggingface.copaper

Your Benchmark Is an Empirical Measure Over Difficulty

The paper treats a benchmark as an empirical measure over item difficulty and formalizes two failure modes: measure mismatch (benchmark difficulty distribution differs from the intended one) and coverage gaps (uncovered difficulty regions that hide localized training progress). It proposes two diagnostic metrics with theoretical guarantees and analyzes 25 popular benchmarks across 7 domains using estimated item difficulties. It also introduces BenchFill, a difficulty-targeted item rewriting algorithm that reduces local coverage gaps.

BenchFill

evals, research· Added 31 Oct 2026

huggingface.copaper

WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training

WorkFactory is a framework that builds coherent, executable professional tasks for training working agents. It plans an information support graph from professional intents, then uses probe executions to find and repair missing or inconsistent task information. The authors built 112,686 tasks across 612 occupations and fine-tuned Qwen models at 4B, 27B and 35B-A3B (WorkPilot). WorkPilot-35B-A3B rose from 879 to 1565 Elo on GDPval-AA v2.1.

QwenHugging Face
WorkFactoryWorkPilotGDPval-AA v2.1

training, agents, research· Added 30 Oct 2026

deploymentsafety.openai.compaper

GPT-Rosalind-6 System Card Addendum

GPT-Rosalind-6 System Card Addendum describes OpenAI's life-sciences reasoning model, which uses the same weights as GPT-6 Astra and is offered only through trusted access. It reports life-science benchmark gains over GPT-Rosalind-5.5 (MedChemBench v7 49.6% vs 28.9%), High-capability Biological and Chemical Preparedness results, and below-threshold Critical bio design evaluations. It also covers access controls, refusal evaluations, cyber jailbreak regression and alignment tables.

GPT-6 AstraGPT-Rosalind-6GPT-Rosalind-5.5
OpenAIPreparedness FrameworkMedChemBench v7+16

ai-safety, evals, models· Published and added 30 Oct 2026

arxiv.orgpaper

world2vec: Mechanistic world models through latent dynamics learning

world2vec is a method for learning mechanistic world models from observations and actions alone, without reward information. Its latent dynamics reproduce the true system over long prediction horizons using at least one order of magnitude fewer parameters than DreamerV3, TD-MPC2 and LeWM. The authors report state-of-the-art control of continuous environments from pixels and accurate system identification across a benchmark of 71 attractors.

world modellatent dynamics learning
world2vecDreamerV3TD-MPC2+2

research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races

TextSeal2 is a distortion-free watermark for LLM output that keeps its signal under speculative decoding. It merges two or more keys into one virtual key coupled to fresh noise through AutoMark's Gaussian copula, and verifies drafts with an extra exponential race. On three LLMs it detects 8 to 22 points more 100-token answers than TextSeal at a 10^-3 false-positive rate.

LLMspeculative decodingGumbel-max watermarking+1
TextSeal2TextSealAutoMark+2

research, inference· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

RADIOlogy: A Single-Pass Approach to Training-Free Zero-Shot Anomaly Detection

RADIOlogy is a training-free, single-pass zero-shot anomaly detection method that uses multi-head attention pooling in vision-language models. It scores anomalies by contrasting average similarity between vision features and sets of normal and abnormal prompts, with no windowed execution. RADIO agglomerative features drive a dense refinement pipeline for pixel-level segmentation, and the method is applied to medical images.

CLIPRADIOvision-language model
RADIOlogyarXiv

research, multimodal· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

VeriCUA is a platform-agnostic framework that verifies task completion by computer-using agents through agentic exploration. The verifier inspects context to build a task rubric, then picks GUI or code checks for unresolved requirements and combines findings under explicit evidence rules. It works online and offline across desktop, mobile and web, and agrees better with reference labels than the baselines, with the largest offline gains on hard cases.

vision-language modelVeriCUA
arXiv

agents, evals, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Multi-View MoE: Letting Every Router Shape Expert Computation

Multi-View MoE is a sparse mixture-of-experts design that uses several independently initialized routers to select experts, then reuses their relative scores to mix learned latent views into each selected expert's input. Each expert still runs one forward pass, so active-expert count, FLOPs and all-to-all volume are unchanged. On a 24-layer 10B-A1B model trained on 708B tokens, it gains 1.18 points on a nine-task mean; Multi-Router alone gains 0.6.

Mixture of ExpertsTransformerMulti-View MoE+1
arXiv

research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

On the Fundamental Limits of Prefill-Based Decoding Length Prediction

This paper derives bounds on predicting an LLM's decode length from prefill-phase hidden states, a primitive for inference scheduling. It models decoding as a stopped stochastic process, giving per-prompt normality and an affine variance law σ=αμ+b. Predictors (MLP, EGTP, FiLM, soft-label, Mixture-of-Experts) converge near the bound, so system error dominates model error. It proposes fixing model, data and sampling in benchmarks and reporting relative-error metrics.

LLMMixture of ExpertsMLP+2
arXiv

research, inference, evals· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Efficient Scalable Oversight via Rewinding

Rewindable interactive proofs (RIPs) are a new model of relativizing interactive proofs for scalable oversight, in which a weak verifier can rewind an AI prover to an earlier saved state. The paper builds an RIP for computations robust to changes in a small fraction of oracle answers. The honest prover runs in linear time, the verifier runs in nearly linear time in the input length after one-time preprocessing, and no cryptography is used. A preliminary MNIST experiment shows an RIP can be faster than a deployed proof system.

rewindable interactive proofsdebaterelativizing interactive proofs
arXivMNIST

research, ai-safety· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

PhysCount: Do MLLMs Count Visual Appearances or Physical Entities?

PhysCount is a benchmark of 546 real-world images and 4,595 human-written questions in 651 target-specific groups. It tests whether multimodal LLMs can separate visible appearances (direct view, reflections, glass) from the physical entities behind them. Across 40 MLLMs, counting appearances is much easier than linking them to entities, and the best model answers every question correctly in only 13.36% of groups.

vision-language model
PhysCountarXiv

evals, multimodal, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Glance: The Generator Is Its Own Reranker

Glance is a RAG method in which the generator also reranks. It adds a lightweight decision adapter and pointer head that score candidate passages from one shared prefill, so a single resident 9B backbone does generation and reranking. After 39 minutes of MS MARCO fine-tuning it reaches nDCG@10 of 0.741 on SciFact and 0.345 on NFCorpus, against 0.721 and 0.326 for bge-reranker-v2-m3. On 300 HotpotQA questions it improves answer F1 by 0.045 over cross-encoder-selected context. Evaluation covers two retrieval datasets, one QA dataset and one backbone family.

RAGLLMbge-reranker-v2-m3
MS MARCOSciFactNFCorpus+1

llm-apps, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation

On-policy state training is a method for training chain embedding retrievers for multi-hop RAG on the states the encoder itself reaches, including those built on its own wrong retrievals. Each state is labeled with the earliest missing gold passage, other missing gold passages are masked, and updates are contrastive and mixed with teacher-forced states. It retrieves complete evidence more often than teacher-forced training and graph-based systems, and transfers to harder long-chain HotpotQA and 2WikiMultiHopQA variants the authors built.

RAGon-policy state trainingcontrastive learning+1
HotpotQA2WikiMultiHopQAarXiv

research, llm-apps, training· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records

CEDAR (Clinical Evidence-Driven Agent for Risk-prediction) is an evidence-citing, self-auditing LLM pipeline for predicting pediatric diabetes outcomes at 24 months from 18 months of records. On 2,489 youth with type 2 diabetes and 4,018 with type 1, pooled AUROC was 0.815 versus 0.656 to 0.700 for trained ML in T2D, and 0.756 versus 0.603 to 0.631 in T1D. Only 4 of 70,246 cited values mismatched the chart. Two pediatric endocrinologists matched its predictions in about nine of ten cases.

LLM
CEDARarXiv

research, agents· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables

EpiCoach is an agentic system that treats one cross-country mountain biker as an N-of-1 experiment. Claims live in an evidence-gated hypothesis registry, and each must make a probabilistic prediction before a session. Predictions come from a digital twin fitted to heart rate, GPS and altitude. In a replay over eighteen months the twin beat standard forecasters on heart rate but not segment time, and the agent loop matched a static model. In the first three live weeks, the ledger sealed 20 predictions and scored 14, and a safety officer vetoed the agent twice. The registry, benchmark and protocol are released.

LLMBayesian experimental designdigital twin+1
EpiCoacharXiv

agents, research, evals· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation

CORAL (Cognitive Resource Self-Allocation) is an agent-callable working-memory toolset that lets an LLM agent checkpoint task progress and verified facts, then reset its cluttered context and resume from a clean state. A Multi-episode Agentic Reinforced Policy Optimization algorithm trains the checkpointing. With an 8B model it reaches 42.8% average accuracy on GAIA, uses 6-7x fewer input tokens than a ReAct agent, and adds 8.0 points to a proprietary agent on BrowseComp.

LLMReActCORAL
Multi-episode Agentic Reinforced Policy OptimizationGAIABrowseComp

agents, research, training· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

A Unified Hessian-Guided Framework for Post-Training Quantization

This preprint proposes a unified post-training quantization framework for large language models. It derives a Hessian-guided approximation of the output change caused by joint weight and activation quantization, using a tractable Fisher approximation. Quantization ranges, linear transformations and weight rounding are optimized together under one output-sensitivity objective. The authors report gains over state-of-the-art transformation and rounding methods in channel-wise and block-wise settings.

LLMpost-training quantizationHessian-guided approximation+1
arXiv

research, inference· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Decompose, Estimate, Select: Coverage-Aware Context Construction for Long-Form RAG

Decompose, Estimate, Select is a coverage-aware retrieval pipeline for long-form RAG. It splits a query into subquestions, ranks candidates with a coverage-trained bi-encoder, predicts a document-by-subquestion coverage matrix with a cross-encoder, and picks documents by greedy maximum-marginal coverage. On TREC RAG 2024, α-nDCG@10 rises from 0.625 to 0.702 (gold-nugget bound 0.718). A grounded self-feedback loop raises V_strict by 0.086 over two passes.

RAGbi-encodercross-encoder+1
TREC RAG 2024α-nDCG@10V_strict

llm-apps, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

MAServeBench is a benchmark that treats multi-agent collaboration as a configurable dimension of LLM serving workloads. Its composable stages model how agents coordinate and exchange context in documented multi-agent workflows, and Hierarchical Semantic Traces record operations and dependencies for reproducible comparisons. Task-linked measurements tie workloads to GPU/NPU behavior, showing serving efficiency does not always mean timely task completion. Code is released.

LLM
MAServeBencharXiv

evals, inference, agents· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets

This paper measures the energy cost of speculative decoding in SGLang with CUDA graphs on H100 and H200 GPUs, at batch sizes up to 64 across 5 corpora. Savings depend on drafted-token acceptance, which is lower on conversation than code and lower on Romansh than English. Savings shrink as batch size grows, and block drafters can push verification into the compute-bound regime, where speculation raises energy per token.

SGLangCUDALLM+4
NVIDIAarXivRomansh

inference, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Benchmarking color judgment in multimodal LLMs with CIE-computable ground truth

A five-task benchmark tests multimodal LLM color judgment against CIE colorimetric ground truth: AWB pair judgment, skin-tone bias direction, CCT estimation, Delta E 2000 pair ordering, and color naming under changing illuminants. Eight endpoints were tested. On ColorChecker-24 stimuli, closed frontier models reach CCT MAE of 715-1056 K versus 1358-2133 K for open-weight models, and a non-ColorChecker control shows this gap is partly template-dependent.

vision-language modelQwen3-VLGLM+2
GLM-4.5VGPT-5.4Claude-Opus-4.7+4

evals, multimodal, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution

Turing LLM post-training combines calibrated multi-teacher on-policy distillation (C-MOPD) with an execution path for dynamically routed mixture-of-experts models. C-MOPD matches each teacher on a local Top-K support with teacher-wise loss normalization and clipping. On Turing-20B-A2B it scores 0.9988 on four-domain integration, beats Qwen3-8B on math and code (85.92 vs 80.33 mean), and cuts consolidation step time from 398.7 to 139.3 seconds in a PPU profile.

Mixture of ExpertsC-MOPDon-policy distillation+1
Turing-20B-A2BarXiv

training, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models

M-PFT is an angular-margin method for prompt tuning of vision-language models that fixes base-to-novel dual miscalibration (underconfidence on base classes, overconfidence on novel classes). It adds two losses: minimizing the maximum cosine similarity between tunable class embeddings, and minimizing angular distance to each zero-shot embedding. Tests on 9 prompt-tuning methods and 15 datasets show lower novel-class calibration error at comparable accuracy and negligible overhead.

vision-language modelprompt tuning
arXiv

research, multimodal, training· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding

MedCBR is a two-stage alignment framework for medical vision language models. Difficulty Weighted Boundary Preference Optimization (DBPO) trains on counterfactual preference pairs at the model's capability frontier. Entropy Gated Grounded Policy Optimization (EGPO) then applies distilled clinical rubrics according to prediction entropy. It reaches 61.2% average accuracy on six medical benchmarks, with the largest gains on differential diagnosis, and the two stages combine super-additively.

vision-language modelpreference optimizationreinforcement learning
MedCBRDifficulty Weighted Boundary Preference OptimizationEntropy Gated Grounded Policy Optimization+1

research, training, multimodal· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories

RetroChessBench is a 12-task benchmark for retrograde chess: reconstructing legal game histories, exact-length constructions, unique endings and exhaustive answer sets, with references, rubrics and a terminal-reward RL environment. GPT 6 Astra High fails to give the required final answer in 22 of 24 attempts without tools and 18 of 24 with code execution. Mean terminal RL rewards are 14.75% and 27.19%. The authors link the failures to scarce worked derivations in web training data.

GPT-6 AstraLLM
RetroChessBench

evals, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

Sparse Autoencoders as Implicit Diversification Regularisers for Cross-Sectional Cryptocurrency Returns

This arXiv preprint (October 2026) tests a sparse autoencoder as a factor model for daily cryptocurrency returns, with equities as a secondary test. SAE portfolios show consistently lower volatility than common benchmarks, linked to lower correlations among selected assets. They do not beat a simple contrarian strategy on risk-adjusted return, and factor identities change between training runs.

sparse autoencoder
arXiv

research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3

DICE is a blockchain-powered federated learning (BCFL) algorithm for customizing large pretrained models among untrusted Web3 participants. It combines dynamic progressive learning and model slice verification, so hardware-limited participants can train part of the model, with a tree-structured committee consensus protocol and an efficiency-driven incentive scheme to scale to more data holders. Experiments cover vision and language models.

federated learningblockchain-powered federated learningprogressive learning+1
arXiv

research, training· Added 31 Oct 2026, published 29 Oct 2026

x.compaper

Cryptography and Security Papers (@FSFG) on X

PrivacyEvalClaw is a tool-augmented deliberative agent for auditing privacy leakage in LLM responses produced under jailbreak prompts. By Krishna Kanth Nakka and five co-authors, the paper is on arXiv (cs.CR) and accepted to AACL-IJCNLP 2026. The fetched post gives only the title, authors and venue, so method details and results are not available here.

LLM
PrivacyEvalClawKrishna Kanth NakkaAACL-IJCNLP 2026+1

evals, agents, ai-safety· Added 30 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication

Proof-Carrying Messages (PCM) is a protocol where each claim an AI agent sends carries evidence: records from an append-only Merkle log the agent cannot write, with inclusion proofs, signed by an attesting signer. Receivers verify offline in about 1 ms and label each claim proven, unproven or failed. On 926 messages (712 lies in 16 classes), PCM accepts 10 lies (1.4%), all stale evidence; plain A2A accepts all 712.

A2AModel Context ProtocoluAgents+5
arXiv

agents, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper

TrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics

TrussTutor-Bench is a benchmark of 200 verified two-dimensional truss problems from statics, paired with automatically generated student solutions. It evaluates thirteen LLMs on solution accuracy (64.5% to 97.0%), error detection (90.4% to 100%) and sycophancy. Models rejected their own correct solutions in 1.6% to 50.0% of cases when a student insisted the work was wrong. Sycophancy separated models; error detection did not.

LLM
TrussTutor-BencharXiv

evals, research· Added 31 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Gold vs.~Translation: Are We Measuring Language, Knowledge, or Locality in Translated Benchmarks?

Gold vs. Translation is an October 2026 arXiv study of whether DeepL-translated MMLU measures the same thing as native benchmarks. It compares seven pairings against six native benchmarks in five Nordic and Baltic languages, using 29 models. Translated MMLU adds predictive value for curriculum-overlap benchmarks such as Skolprov (ΔR²=.128) but not for Sweden-specific SwedishFacts (p=.242).

LLM
MMLUDeepLSkolprov+2

evals, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

This paper studies whether vision-language models can infer how long a person stays somewhere (living, staying, or leaving) from geotagged social media posts. The authors build a new corpus of geotagged tweets co-annotated by humans and LLMs. State-of-the-art models struggle even with multi-turn Chain-of-Thought prompting, often missing contextual cues and subtle hashtags while over-relying on prominent visual details.

vision-language modelLLM
arXiv

research, evals, multimodal· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

inkGround: Benchmarking Fine-grained Visual Grounding Capabilities of Vision-Language Models for Cursive Handwriting in the Wild

inkGround is a benchmark for stroke trajectory recovery from full-page, camera-captured handwriting, with 537 page images (about 18.7k words, 163k strokes) and pseudo-label references filtered by OCR agreement and human raters. Models get a page image and a target word, then output ordered stroke points. Seven VLMs were scored with DTW, Chamfer distance, readability and style similarity. Closed-source models, notably Gemini-3.1-Pro, did best, and the ranking held on IAM-OnDB.

vision-language model
inkGroundIAM-OnDBGemini-3.1-Pro+1

evals, multimodal, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Deogen: Automatic Benchmark Generation for Reasoning over Policies

DeoGen is an automatic, parametrizable benchmark generator for deontic reasoning, where a model applies policy rules to facts to reach a verdict. It autoformalizes rules into first-order logic, builds decision trees, and turns each tree path into a benchmark entry. Frontier models give the correct verdict 89-92% of the time, but only 22-40% on entries lacking enough information, even when told to abstain.

LLMfirst-order logic
DeoGenarXiv

evals, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding

AskStream is a multi-turn benchmark for streaming video understanding that adds a third proactive action, ask, alongside wait and answer, for cases where video or user information is incomplete. It has 438 videos, 2,714 manually annotated frame-level time windows (wait, ask, answer), four task categories and eight subtasks. The strongest model reaches only 52.18% on the proposed Ask-F1 metric, in both multiple-choice and open-ended settings.

multimodal large language model
AskStreamAsk-F1arXiv

evals, multimodal, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models

QbD-VLA is a mixed-precision post-training quantization method for vision-language-action models. It uses task success from short closed-loop evaluations to assign weight and activation bit widths, accounting for interactions between components. On four VLA models across all four LIBERO suites it holds task performance at about 4-bit weights and under 6-bit activations. The gain on SIMPLER is small. On a Franka Research 3 arm, X-VLA shows no detected loss, but π0.5 fails.

vision-language-action model
QbD-VLALIBEROSIMPLER+4

research, inference, multimodal· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study

This paper replicates Chen et al.'s study of LLM-based smart contract vulnerability detection, first on GPT-4 and then on Mixture-of-Experts, RNN-like and State Space Models. The exact replication confirms the high-recall, low-precision pattern on GPT-4. The differentiated replication finds the pattern does not transfer uniformly: GPT-4 and Gemma-3 behave alike despite a roughly 100x parameter gap, while two MoE models diverge.

LLMTransformerMixture of Experts+3
Chen et al.GPT-4Gemma 3+1

research, evals· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Think Before You Act: Decision Gate for LLM Agents

JevAct is a runtime verification framework that intercepts selected LLM agent actions before execution and returns feedback for bounded revision. It compiles domain policies into executable state checks and structured questions scored by a prefill-only decision model, giving probability-based judgments without generation. Tested on eleven agents with tau^2-bench Airline and Telecom and BFCL, it gained consistently on Telecom and BFCL and was mixed on Airline.

LLM
JevActtau^2-benchBFCL+1

research, agents, evals· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Repairs for Whom? Evaluator-Executor Mismatch in Selecting Repairs for Failed LLM Agents

Repairs for Whom? studies single-step repairs of failed LLM agent trajectories and asks whether common evaluators (greedy replay, stronger models, oracles, log-reading judges) pick repairs that help the deployed agent. Using independent rollouts in ALFWorld and WebShop, greedy replay loses 0.06-0.13 in expected gain, and Qwen2.5-14B rollouts misselect repairs for Qwen2.5-7B. The authors recommend verifying repairs with the executor that will run them.

LLMQwen
ALFWorldWebShopQwen2.5-7B+2

research, agents, evals· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Data Scaling Laws in Stereo Matching: From In-domain Fitting to Cross-domain Generalization

This paper studies data scaling laws in stereo matching and releases XStereo, a realistic synthetic dataset of 200 thousand samples. In-domain training on five large datasets shows two regimes: a standard power law, then saturation, with a transition point roughly fixed for a given model. Cross-domain performance depends only weakly on source data scale, and distribution and coverage diversity reduce domain gaps more.

XStereoarXiv

research, training, multimodal· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Session-Bound Behavioral Watermarking for Autonomous LLM Agents

AgentAnchor is a session-keyed behavioral watermark that lets an agent owner prove ownership of a trajectory log. Each step key comes from a secret key, a fresh public session identifier and semantic states of recent observations. Parity evidence is embedded through a KL-bounded exponential tilt of action choices. A trusted verifier checks disputed logs without rerunning the agent, using wrong-key calibration and abstention. The paper also formulates a learned cross-session forgery threat.

LLM
AgentAnchorarXiv

research, agents· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

CALM is a conflict-aware lifecycle memory governance framework for long-horizon language agents. It turns records into evidence-grounded memory cells, updates their validity and lifecycle states from support, conflict and dependency signals, and admits evidence at query time through training-free or learned gating based on temporal applicability. It beats baselines on LongMemEval-S and LoCoMo with Qwen and GPT backbones, and keeping superseded records helps earlier-state reasoning.

LLMQwen
CALMLongMemEval-SLoCoMo+1

agents, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

This paper measures job-based doubt in LLM fact-checkers: judging a claim false more often when the poster has a lower-status job. It compares base and post-trained checkpoints of six model families on fact-checked claims with randomised poster profiles. Only the open Tülu-3 recipe (OLMo-2 32B, Tülu-3 70B) creates the effect, under one percentage point but reliable. In OLMo-2 32B the flip comes from one residual-stream direction and appears at supervised fine-tuning, confirmed on 400 new claims. None of seven commercial models doubts lower-status posters more.

LLMTransformer
OLMo-2 32BTülu-3Tülu-3 70B+3

research, ai-safety, training· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Benchmarking decision models against generative large language models on medical multiple-choice questions

This preprint benchmarks 13 decision models against 15 generative LLM configurations, including different reasoning settings, on 1,273 text-only four-option MedQA questions. Accuracy ran 67.71% to 89.08% for decision models and 78.32% to 96.86% for generative configurations. Decision models were cheaper and faster, but answers with probability of at least 0.90 still had error rates of 1.71% to 12.77%, and probability repeatability varied across three runs.

LLM
MedQAMercury DecideClef Omni+1

evals, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training

This paper measures how much a model's final answer depends on its own written chain of thought, using a synthetic box-swap task with exact ground truth. It edits one step in the model's chain to a wrong but valid state and checks whether the answer follows. Across 25 open-weight models, reliance rises with size and saturates (Qwen3 from 16-18% at 0.6B to 97-100% at 14B). Reliance tracks capability (r = 0.99) and is unchanged by post-training.

Qwen3GemmaLlama+2
Gemma 3Llama 3arXiv

research, ai-safety, evals· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering

TCC-RAG is a retrieval-augmented generation method for temporal knowledge graph question answering (TKGQA). It turns the temporal knowledge graph into a multi-view causal cue graph, builds a query-specific temporal causal chain to guide retrieval, and applies a causal evidence filter to the results. The authors report gains of 10.72% and 8.40% on two TKGQA benchmarks and 62.97% on multi-step temporal reasoning.

RAGLLM
arXiv

research, llm-apps· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

FlatCake: A Flat KVCache Storage Architecture for LLM Serving

FlatCake is a KV cache storage architecture for LLM serving that treats host DRAM and NVMe SSD as peer media in one 64-bit address space, instead of a DRAM-over-SSD tier. Blocks are placed once, in session-contiguous, layer-major order, and streamed via GPUDirect Storage. On a Claude Code trace with DeepSeek-V4-Flash it holds a 94% hit rate (Mooncake: 64%) and cuts peak-load mean TTFT 1.6x.

GPUDirect StorageNVMe SSDLLM+3
FlatCakeMooncakeMooncake-GDS+3

inference, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Multi-Token Prediction Done Right

Soft Multi-Token Prediction (Soft-MTP) is a one-line change to multi-token prediction (MTP) pre-training. The authors show the MTP cross-entropy gradient splits exactly into a KL self-distillation term and a noisy residual, and a straight-through "KL gradient-recovery trick" keeps only the KL term. From 167M to 1.2B parameters it gives lower NTP perplexity, faster speculative decoding and higher zero-shot accuracy than standard MTP, with no added parameters or overhead.

LLMTransformer
DeepSeekMeta

research, training· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Complementing Text Based Moderation with Multimodal Grounding: Detecting Fraudulent Inducement Behaviors on Short Video Platforms

The paper studies detection and temporal localization of fraudulent inducements (prompts to follow, join chat groups, click links) in internet finance short videos. It compares OCR+LLM, OCR+MLLM and a zero-shot MLLM, and builds a dataset of 2,419 videos (66.49 hours, 3,194 events, four categories). OCR+MLLM reaches mIoU 26.52 versus 14.49 for keyframe OCR+LLM, with 67.0 percent macro recall, using a recall-weighted F2 localization reward.

MLLMLLMOCR
arXiv

research, multimodal, training· Added 30 Oct 2026, published 28 Oct 2026

huggingface.copaper

What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents

This paper treats LLM reasoning effort as a credence good and measures the counterfactual effect of effort levels on proprietary and open-weight models across four benchmarks, including long-horizon agentic tasks. Higher effort often fails on tasks lower effort solved, and on easy tasks the top level costs up to 42x the lowest. Starting at the lowest effort and escalating only after a verified failure matches or beats fixed top effort, usually at lower cost for proprietary models.

LLM
Hugging Face

research, evals, agents, ai-policy· Added 28 Oct 2026

arxiv.orgpaper

Post-Training Large Language Models with LLMON

LLMON (LLM Object Notation) is a framework that separates executable instructions from passive data and requires explicit identifier-based execution. The paper post-trains Granite-4.1 3B and 8B base models on a 4.6B-token corpus of general, RAG and tool-calling data with distractor variants, using SFT then RL. Attack success rates on indirect prompt-injection benchmarks fall from 53-100% to 0.02-5.6%, with general capabilities preserved. It also adds attention-based per-layer diagnostics.

LLMRAGTransformer
LLMONGranite-4.1arXiv

training, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper

Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition

This paper proposes an fMLLR-based compensation mechanism that cuts the fine-tuning data needed in transfer learning for speech emotion recognition under train-test acoustic mismatch. An autoencoder reduces trainable parameters, and an affine transform in the encoder latent space models rotations and shifts. In a human-robot interaction task, mean CCC rose 16.8% with 12.9% of the training set and 14.4% with 50%.

fMLLRautoencoder
arXiv

research, multimodal, training· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence

The paper proposes POB-ICM (contingency matrix with Chi-square independence testing) and POB-UNBP (a uniformity null model under permutation-based evaluation) to detect positional bias in top-1, single-turn LLM recommenders. On a RAG product-recommendation testbed with 2000 queries and 20 permutations each (40,000 instances), both methods reject positional independence in all evaluated models. Three metrics quantify the effect, and the bias persists across candidate-set size and temperature. Code is public.

LLMRAG
arXivPOB-ICMPOB-UNBP

research, evals, llm-apps· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Locating Sycophancy Across Training Stages in Open Language Models

Locating Sycophancy Across Training Stages in Open Language Models measures sycophancy in 13 open checkpoints from 5 lineages, from base model through supervised fine-tuning and preference optimization to release. It finds two behaviors with different origins: deference to a claim in the prompt exists in every base model, while capitulation under user objection is largely absent from base models and present in every post-trained checkpoint. Post-trained models often drop firmly held answers as readily as loosely held ones when the objection names an alternative.

LLM
arXiv

ai-safety, research, evals· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

Heads of Security (HoS) is a prompt injection defense that trains a small set of per-head attention gates to shift attention between trusted and untrusted tokens, separating instructions from data. Tested on Llama-3.3-70B-Instruct and GPT-OSS-20B, the black-box RL-Hammer attack reaches 10% ASR on HoS versus 97% on base GPT-OSS-20B and 85% on SecAlign. HoS keeps base utility in few-shot settings, where SecAlign and ASIDE degrade.

TransformerLlamaLLM
Heads of SecuritySecAlign++SecAlign+5

research, training· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Can LLMs Uncover Hidden Physical Laws through Free Exploration?

LongChang is an automated framework that builds simulated worlds with altered physical laws, such as heavier objects falling more slowly, to test whether LLMs can find the law by free exploration. Explorer LLMs manipulate objects and build tools without tasks or hints, while separate LLM agents generate scenes, review tool designs and grade reports. Across 12 LLMs, GPT-6 Astra reached a 16.7% discovery rate and the other 11 scored 0%.

LLM
LongChangGPT-6 AstraarXiv

evals, research, agents· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis

SynthAPI is a pipeline that generates synthetic tool-use environments with explicit control over diversity of tools, tasks and underlying databases. Across 458,752 tasks and 849 trained models of four sizes, the authors fit a scaling law predicting downstream agent generalization. At larger data budgets, scaling tool and database diversity beats adding more tasks, and higher complexity helps more. Agents trained this way beat prior synthetic-data baselines on four benchmarks.

LLM
SynthAPI

research, training, agents· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Metacognitive Decoding: Efficient Inference for Diffusion Language Agents

Metacognitive Decoding is a lightweight plug-in controller for diffusion language model backbones. It learns when to finalize tokens and how far generation should extend, and is trained on agent trajectories to balance correctness against generation cost. Across five benchmarks it cuts inference FLOPs by 20.6% on average versus the most efficient baseline, with competitive task accuracy. The abstract names no specific benchmarks or backbones.

diffusion model
arXiv

research, agents, inference· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Know, then Draw: A New Learning Paradigm for Visual Generation

Know, then Draw is a learning paradigm for visual generation that uses autoregressive pretraining to acquire semantic knowledge and diffusion post-training for high-fidelity rendering. Controlled comparisons find autoregression the stronger pretraining objective, and semantic quality matters more than AR-only generation quality. This motivates a purely semantic tokenizer trained with language supervision only. A 3B text-to-image model trained in 6,600 H100 GPU-hours scores 86 on GenEval and 87 on DPG-Bench.

diffusion modelTransformer
arXivGenEvalDPG-Bench+1

research, multimodal, training· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Perceiving and Predicting Dynamic Sports: Spatiotemporal Intelligence in Vision Models for Egocentric Tennis Video

This paper presents an annotated egocentric tennis dataset (egocentric video synced with five allocentric views, global positions, contact times, stroke types) and evaluates image encoders, video encoders and vision-language models on seven prediction tasks. Best models reach 0.14 m player and 0.54 m ball localization error and 0.14 s contact-time error. Depth input helps 3D ball localization, and longer histories do not help forecasting. A conditional diffusion model generates whole-body tennis motion in real time.

vision-language modeldiffusion modelTransformer
arXiv

research, multimodal, evals· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

VideoLVR: Latent Visual Reasoning over Grounded Video Evidence

VideoLVR is a method that lets video multimodal LLMs build latent visual evidence from local regions at relevant moments and reason over it interleaved with text tokens. A visual token prediction objective, defined over a vocabulary derived from the input video, supervises the latents. It extends to reinforcement learning with sampled visual tokens as actions and final-answer rewards, and improves fine-grained video benchmarks without much context growth.

vision-language modelLLM
VideoLVRarXiv

research, multimodal, training· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

EnvSched is an online scheduler for agentic reinforcement learning that picks which environment-task pairs to roll out next. It builds a dual-relation graph over environments and tasks, propagates past rollout statistics to predict within-task reward variance, and adds environment quotas and a similarity penalty. On Qwen3-8B it scores 48.81 average on BFCL-v3, tau-Bench and ACEBench-Agent after 40 steps, above random selection at 120 steps.

Qwen3
BFCL-v3tau-BenchACEBench-Agent+1

training, agents, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does

This paper defines a character naming task for films: given a name spoken in dialogue and its video context, the model must pick which visible character bears that name. It provides a dataset with annotations for character naming and first appearances, a video-and-dialogue model, and a comparison with proprietary multimodal LLMs. It also proposes a progressive framework that builds a character bank as the film plays, without cast lists or actor photographs.

multimodal large language model
arXiv

research, multimodal· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Interpretable Meta-Policies for Neural Decision Making

NEXUS is a hierarchical reinforcement learning framework that pairs neural skills with symbolic meta-policies, so transparent reasoning sits at the level of high-level skills rather than atomic actions. It uses object-centric observations and LLM interaction to design reward functions and meta-policies. Agents learn disentangled skills, align better with goals in the game manual, resist reward hacking more, and cope better with game simplifications than deep RL. The paper also compares neural, symbolic and neuro-symbolic meta-policy architectures.

LLM
NEXUSarXiv

research, training, ai-safety· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

CRISP: Co-designing Pruning and Scheduling for Efficient MoE Inference on Edge Servers

CRISP is a combination-aware framework that co-designs pruning and runtime scheduling for Mixture-of-Experts inference on memory-constrained edge platforms. It reorders neurons by importance so one stored expert supports several execution widths, gives hot, warm and cold expert combinations different widths, and overlaps expert loading with computation. On Mixtral-8x7B and DeepSeek-MoE-16B it raises throughput up to 2.1x at the same memory budget, with accuracy loss limited to 3.6%.

Mixture of Experts
Mixtral-8x7BDeepSeek-MoE-16BarXiv

inference, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

FeatureArc: Benchmarking Coding Agents on Evolving Features

FeatureArc is a benchmark for coding agents on evolving features, built by a pipeline that mines repository histories into multi-stage tasks across four programming languages. It has 73 manually reviewed tasks of 2 to 10 stages, validated with fail-to-pass and pass-to-pass tests. Across 10 agents, pooled success drops from 62.7% at the first stage to 28.5% for the whole feature. Inherited defects appear in 72.9% of failed later stages.

LLM
FeatureArcTencentHunyuan+1

evals, coding-agents, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

When Visual Evidence Is Insufficient: How Instructions, Post-Training, and Internal Activations Shape Refusal in Multimodal Language Models

This paper studies how multimodal LLMs refuse questions that an image cannot answer, using the MoHoBench benchmark on three MLLMs. It varies the meaning and placement of refusal instructions, compares supervised and preference-based post-training, and intervenes on a refusal-related activation direction. Instructions change refusal at the sample level in ways aggregate rates hide. Post-training raises refusal most but can mix refusal with attempted answers. Activation intervention gives smaller, transferable changes.

vision-language modelLLM
MoHoBencharXiv

ai-safety, multimodal, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Bayes-Adaptive MDPs for Rollout Allocation to Enhance GRPO Training

AdaRoll-GRPO is a method that allocates GRPO rollout budgets per question by difficulty instead of uniformly. It frames allocation as a sequential decision problem and learns an allocation policy with a Bayes-adaptive MDP, computed offline so training adds no online optimization cost. Experiments on several reasoning datasets and LLM architectures show gains over standard GRPO at the same total rollout budget.

GRPOLLM
AdaRoll-GRPOarXiv

training, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG

This paper studies a cost-aware, two-action RAG routing policy that chooses between dense retrieval plus reranking and a hybrid lexical-dense retriever, using a regularized linear model to predict per-question evidence gain. On 60 held-out QASPER articles (188 questions), it triggers hybrid retrieval on 24.5% of questions and matches always-hybrid Hit@10 (78.70%). Answers from 4-bit Qwen3-4B show no clear correctness or faithfulness gain, and the assessments are model-assisted.

RAGQwen3BM25
QASPER

research, llm-apps, evals· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

LiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents

LiveSearch is a live benchmark for financial search agents that stores each question as executable verifier code: a typed program of calls to a professional financial data service plus a declarative extractor. Gold answers are recomputed daily with no human or LLM in the loop, so memorized answers go stale. Six tool-calling models score 70.9% to 76.7% under web search, and 70% of questions change gold value over three days.

LLM
LiveSearcharXiv

evals, agents, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents

OpenGray is a benchmark that adds tasks with known correct decisions to the OpenKBP-Opt head-and-neck dataset, including two overlap contradictions with provably incompatible dose goals and a feasible control. Four planning systems, from a rule-based script to a full LLM agent, were tested on 30 patients with Terra and Ministral 3 8B. Decision accuracy reached 95.4% and 92.1%, yet only 50% and 25% of overlap contradictions were escalated. SAGE logs of 39 radiosurgery runs showed an agent that lacked an action for stopping.

LLM
OpenGrayOpenKBP-OptSAGE+3

evals, agents, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Tessera: Structure-Completed Evidence Units for Web Retrieval-Augmented Generation

Tessera is a training-free evidence delivery layer for web retrieval-augmented generation. It rebuilds retrieved pages' HTML into fine-grained evidence units, each completed with page title, section path and table headers, then packs the relevant units into the reader context at the same token budget. Tracing evidence over full English Wikipedia shows chunking loses table and infobox content. Tessera adds 5 to 6 accuracy points on three QA benchmarks and carries over to agentic search.

RAGHTML
TesseraWikipedia

llm-apps, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization

This paper tests the delta-learning hypothesis for Direct Preference Optimization (DPO), where the larger model's response in a single model pair is treated as preferred. It shows, in theory and experiments, that fixed pairs add generator-specific biases that predict the preference label regardless of quality. DPO on single-pair data underperforms multi-model data, consistent with reward hacking, and adding more generators partly fixes it without an external judge.

LLM
arXiv

training, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

p-DCIM: A 28nm Probabilistic SRAM DCIM based Ising Machine for Near-Memory Context Selection in LLM-RAG Pipeline

p-DCIM is a 28 nm SRAM digital compute-in-memory macro (0.16 mm2, 0.41 mW) that works as an Ising machine for RAG evidence selection. Selection is cast as a QUBO problem, and the same MAC datapath computes embedding similarities and annealing steps. Replacing LLM reranking with it gives a selection-energy estimate over six orders of magnitude lower and cuts total energy per query by 67%, with comparable token-level F1 on the evaluated examples.

RAGLLMSRAM+2
arXiv

research, inference, llm-apps· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models

DCKV is a differentiable codec for the prompt KV cache of hybrid language models, which keep a KV cache only in their few full-attention layers. Transform, quantizer and entropy models (conditioned on prompt tokens and already decoded neighbouring positions) are trained end to end against a frozen model. On Qwen3.5-2B it stores a token in over 55 times fewer bytes than bf16 with at most 1.8 points lost on three long-context benchmarks, and over 100 times fewer with at most 3.6 points lost.

Qwen3.5TransformerLLM
DCKVarXiv

research, inference· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

AxisQ: Depth-Adaptive Channel--Frequency Quantization for Camouflaged Object Detection

AxisQ is a post-training quantization framework for camouflaged object detection (COD) that allocates activation bits by feature depth. It uses the channel domain for shallow features and the local-frequency domain for deep features, under a fixed per-layer average bit budget. It adds a boundary-aware Hessian approximation for reconstruction. On CAMO at W2A2, weighted F-measure improves 12.7% for CFRN and 33.3% for CamoFormer-P over the strongest baselines.

CNNTransformer
AxisQCFRNCamoFormer-P+1

research, inference, multimodal· Added 28 Oct 2026, published 27 Oct 2026

eprint.iacr.orgpaper

OblivDGL: Oblivious Deep Graph Learning Made Practical

OblivDGL is a framework for secure GNN training and inference in machine-learning-as-a-service settings, modelled on Deep Graph Library. It uses an oblivious message passing paradigm and a new oblivious graph representation built on function secret sharing, revealing only the total node and edge counts. On four benchmark graphs it cuts training communication up to 1024x with up to 14.3x speedup, and inference communication up to 754x with 4.19x speedup.

Deep Graph Librarygraph neural networkfunction secret sharing
OblivDGLNDSS

research, training, inference· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper

Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels

The paper folds the per-key logit bias of Attention Matching (AM) KV cache compaction into the keys along one closed-form direction per head, fitted on context queries. The result is a plain cache that FlashAttention and vLLM paged caches can use, with output error bounded by how far each query's projection on that direction is from 1. Unmodified vLLM serves folded caches through a KV connector. On QuALITY and LongHealth the fold is within noise of AM in 13 of 14 settings. Under AM's published per-head budgets it is within noise in 9 of 10.

vLLMFlashAttentionHugging Face+3
Attention MatchingQuALITYLongHealth+2

research, inference· Added 28 Oct 2026, published 27 Oct 2026

huggingface.copaper

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

TraceTrial-Bench is a benchmark that scores agent task performance and agent harness reliability separately. It has 95 mechanism-oriented tasks across seven components: context, execution, governance, lifecycle, observability, tools and verification. Across 4 harnesses, 9 models and 3,420 runs, macro-averaged harness scores range from 59.8% to 72.0%, and 31.1% of runs succeed despite failing at least one harness criterion.

LLMHugging Face
TraceTrial-Bench

evals, agents, research· Added 27 Oct 2026

arxiv.orgpaper

AK_QMUL at ArGuard Shared Tasks: A Single Fine-Tuned JAIS for Arabic Harmful-Prompt Detection

AK_QMUL's system for the ArGuard-2026 shared tasks fine-tunes JAIS-6.7B with 4-bit QLoRA and a linear head on the last-token representation. For binary safe/unsafe detection (B1) it uses a four-way head over dialect register and AraSafe MSA augmentation, reaching macro-F1 0.984. For seven-way harm domain (B2) it averages five seeds, reaching 0.790. Both ranked first. Bully is the weakest class.

JAIS-6.7BQLoRALLM
JAISArGuardAraSafe+2

research, ai-safety, training· Added 28 Oct 2026, published 26 Oct 2026

arxiv.orgpaper

Your Wish Is My Commit: Over-Compliant Refactoring in AI Coding Agents

Your Wish Is My Commit is a controlled study of over-compliant refactoring in Codex and Claude Code, run across five models, 50 algorithmic tasks and 10 object-oriented tasks. Over 3,000 turns of repeated "refactor further" prompts, no model stopped on its own: each rewrote up to 31x the original codebase before first stopping and resumed edits after declaring the task complete. The paper defines six behavioral signals for detecting over-compliance.

CodexClaude CodeLLM
arXiv

coding-agents, research, evals· Added 28 Oct 2026, published 26 Oct 2026

arxiv.orgpaper

Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models

REVA (REal-time Vulnerability Analysis) is a vulnerability detector that puts a module threat model, lightweight static analysis findings and call-graph information into one LLM forward pass. A trained probe reads the model's internal representations of the new function. On PrimeVul's held-out test set, REVA on GLM-5.3-Flash reaches 60.0% accuracy in about one second per function, matching the agentic VulTriage (59.2%) at over 250 times the speed and under a tenth of the cost. The probe is 14% to 17% more accurate than the LLM's own verdict.

LLMstatic analysis
REVAVulTriagePrimeVul+2

research, coding-agents· Added 28 Oct 2026, published 26 Oct 2026

arxiv.orgpaper

SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments

SentryBench is a benchmark for tool-using LLM agents in public-safety deployments. It scores attack success, over-refusal (missing a real emergency) and over-reaction (unwarranted action) on a cost-sensitive frontier, using real emergency-call transcripts, disaster messages and injection payloads. Across 840 episodes on three frontier models and three defenses, refuse-more caution pushed over-refusal to 100 percent on two models, while a trust-gating wrapper gave the lowest harm.

LLM
SentryBencharXiv

evals, ai-safety, agents· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments

SymLift is a compile-free vulnerability detection framework for code fragments that lack project context. A fine-tuned LLM reconstructs control-flow, data-flow, memory and resource relations as a constrained LLVM-like IR, and a deterministic parser turns it into facts for Datalog rules that give findings with derivation traces. SymLift-Qwen-7B reaches 94.41% Target-F1 on FormAI and 91.66% micro-averaged Target-F1 on MegaVul.

LLMQwenDatalog+3
SymLiftSymLift-Qwen-7BFormAI+2

research, training· Added 28 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

Explaining Navigation Decisions: Stage-Aware Visual Attribution for Vision-Language Navigation

A stage-aware visual attribution framework for Vision-Language Navigation (VLN) that explains a robot's action choices. It identifies "instruction-stage insensitivity", where existing explainers give similar outputs across navigation stages. The method builds action-conditioned temporal instruction-visual attributions, aggregates relevant historical evidence by stage, and applies an instruction-guided spatial filter. It improves attribution quality across several VLN policies and benchmarks, helps diagnose failure cases, and was tested on a Unitree G1 robot.

vision-language model
Unitree G1

research, multimodal· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

The Patient Is Always Right? Evaluating Sycophancy in Medical Diagnosis with Graded Patient Beliefs

This paper evaluates sycophancy in medical diagnosis across nine AI models. Each model is shown clinical evidence plus a patient's belief in a specific but incorrect condition, with the belief's closeness to the evidence varied. Models adopted the belief 23.2% of the time on average, even for fictional conditions, and 43.0% under a Rare Disease Claimer persona. Medical fine-tuning and larger scale reduced susceptibility.

LLM
arXiv

ai-safety, evals, research· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine

This paper presents an open benchmark of five existing pseudonymisation tools and a regex baseline on Russian and UK English documents, plus an open engine built on the two strongest tools. On a held-out set of 1,000 synthetic documents per language, the best existing tools leave a whole value visible in 58 to 61% of documents. The engine does so in 0.2 to 0.3%. Russian name restoration reaches only 94.6%, below the 99% threshold. Real documents were not tested.

LLMpii-guard
Vladimir BeskorovainyiarXiv

evals, llm-apps, research· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

Detecting and Understanding Ambiguity in Visualizations with Role-Playing Vision Language Model Interpretations

This paper presents a pipeline that uses persona-conditioned vision language models to surface interpretive ambiguity in visualizations. Topic-relevant personas elicit candidate takeaways, and a Target-Pattern-Scope framework lets LLM judges label statement pairs as Compatible, Disjoint or Opposing, which are summarized in an ambiguity profile. The authors benchmark VLMs on chart comprehension per chart type, check labeling against human annotations, and run case studies on public visualizations and a redesign.

vision-language modelLLM
arXiv

research, multimodal, evals· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

InteractiveWorld is an environment for closed-loop interaction between an AI assistant and a simulated human agent who sees the scene, follows instructions and acts independently. InteractiveBench, built on it, has 120 multi-turn tasks in six categories scored by verifiable, state-based rewards. Across 12 frontier MLLMs, the best model, Claude Fable 5.1, reaches at most 20% on long-horizon Guidance and 25% on Planning tasks.

multimodal large language model
InteractiveWorldInteractiveBenchClaude Fable 5.1+1

evals, multimodal, research· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Continual Learning Exam (CLE) is a benchmark of 120 human-authored tasks, each a five-level ladder (600 levels) across 89 professional roles and 12 occupational domains, built by 50+ domain experts. Agents must pass a level to unlock the next, and an evaluation agent scores submissions against human rubrics. Across 17 harness-model configurations, feedback plus one revision adds a median 5.3 points; the best system clears 47.7% of levels and finishes all five levels in 23.3% of tasks.

LLM
Continual Learning ExamarXiv

evals, agents, research· Added 27 Oct 2026, published 25 Oct 2026

Showing 90 of 756

Show more