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.
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, researchΒ· Added 31 Oct 2026, published 29 Oct 2026
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.
Kolesnikov and Novoselov give block basis reduction (BKZ) algorithms for linear codes that need polynomial or quasi-polynomial numbers of calls to a minimum weight codeword oracle at fixed block size. The earlier Ghentiyala and Stephens-Davidowitz bounds are exponential. The paper adds a truncated BKZ and a DeepBKZ variant, with an implementation for block sizes 2 to 24 and approximation-factor estimates on random codes.
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.
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
researchΒ· Added 31 Oct 2026, published 29 Oct 2026
Addendum to the GPT-6 Luna system card for the model update of 29 October 2026 (the title says October 28). OpenAI keeps the High rating for cybersecurity and biological/chemical capability under its Preparedness Framework. It reports ExploitBench 46.19% and SEC-Bench Pro 51.75% (GPT-6 Astra: 85.4%), higher multiturn jailbreak defender success than the October 7 version, and GPT-Red prompt-injection results. It also reports weaker factuality and dual-use biology refusal.
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 (ΞRΒ²=.128) but not for Sweden-specific SwedishFacts (p=.242).
LLM
MMLUDeepLSkolprov+2
evals, researchΒ· Added 30 Oct 2026, published 28 Oct 2026
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, researchΒ· Added 30 Oct 2026, published 28 Oct 2026
Shor's algorithm compiled on cat qubits is an IACR ePrint (2026/2665) giving an end-to-end resource estimate on superconducting cat qubits, using repetition and LDPC cat codes. Factoring RSA-2048 needs about 23,000 cat qubits and 3.14 days, assuming phase-flip noise p_Z = 5e-4 and no bit-flips. secp256k1 ECDLP needs at most 30,000 qubits and 1 hour. A space-for-time trade runs RSA-2048 in 1.25 hours on about 611,000 qubits.
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 TΓΌlu-3 recipe (OLMo-2 32B, TΓΌlu-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 32BTΓΌlu-3TΓΌlu-3 70B+3
research, ai-safety, trainingΒ· Added 30 Oct 2026, published 28 Oct 2026
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-policyΒ· Added 28 Oct 2026
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, evalsΒ· Added 28 Oct 2026, published 26 Oct 2026
SymLift is a compile-free vulnerability detection framework for context-incomplete code fragments. A fine-tuned LLM lifts control-flow, data-flow, memory and resource relations into a constrained LLVM-like IR. A parser turns the IR into facts, and Datalog rules derive findings with derivation traces. On Juliet function-level fragments Clang compilation success falls to 12.00%, while SymLift's completion rate drops only 1.17 points. SymLift-Qwen-7B reaches Target-F1 94.41% on FormAI and 91.66% micro-F1 on MegaVul.
LLMQwenLLVM+2
SymLiftFormAIJuliet+2
AppSec, AI SecurityΒ· Added 28 Oct 2026, published 25 Oct 2026
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, trainingΒ· Added 28 Oct 2026, published 25 Oct 2026
This paper compares LoRA and full fine-tuning for prompt-safety classification using a matched 400M encoder-decoder pair (Ettin) across three task formats, with up to 15 seeds per cell and pre-specified analyses. Full fine-tuning leads LoRA by 2-3 pp at the pre-specified learning rates, and the encoder gap closes when both use the same learning-rate search. Training LoRA to write a reason after its verdict adds 4.0 pp, while a content-free sentence of equal length does not. Trained models beat a prompted 8B in domain but trail it by 8-23 pp on adversarial jailbreaks and over-flag benign prompts (27-66% against 2-3%).
LoRAEttinTransformer
training, research, evalsΒ· Added 27 Oct 2026, published 24 Oct 2026
FORK is a reward for rubric-based reinforcement learning that jointly optimizes recall and a new precision objective. Precision requires each unit of a response to be necessary (rubric-driven necessity credits) and factually correct (a grader). Rubric-coverage rewards otherwise produce verbose, less accurate responses. FORK keeps similar coverage with shorter outputs, raising win rate against the base policy from 10.6% to 68.0% on RubricHub-Medical and from 22.1% to 74.1% on HealthBench.
LLM
HealthBenchRubricHub-MedicalFORK
training, researchΒ· Added 27 Oct 2026, published 24 Oct 2026
The paper formalizes elliptic-curve semiprimality certificates by adapting the Goldwasser-Kilian primality criterion. For certificates built with complex multiplication, a norm-lattice reconstruction factors N from (N, S, D) alone in expected polynomial time. The author uses it, plus public-point and quadratic-twist attacks, to factor Reble's 1084-digit and Broadhurst's 5061-digit moduli, and shows that hidden-cofactor, withheld-CM-map and private-isogeny repairs also fail.
SCI-AGENT-EXAM is a workflow-oriented benchmark of 120 expert-curated tasks across 11 scientific fields and 7 task types from the Scientific Workflow Task Taxonomy (SWTT). Tasks need both executable and textual artifacts, scored by programmatic checks plus an expert-calibrated LLM judge. Ten frontier agents were tested: GPT-6 Astra scored highest at 80.9, but only 26.0% of its runs passed the 0.95 success threshold.
BiLoCo is a post-training quantization method for FP4 LLMs that adds low-rank corrections whose left and right factors are stored as binary Β±1 sign vectors instead of BF16. This uses 16x less storage per rank-one component and lets the correction run on CUDA cores alongside the FP4 tensor-core GEMM. On 4B to 72B LLMs it matches or improves memory-matched SVDQuant. A fused B300 kernel is at most 11% slower than FP4-only GEMM at batch size 1 for ranks up to 512.
CUDALLMdiffusion model
BiLoCoSVDQuantNVIDIA+1
inference, researchΒ· Added 26 Oct 2026, published 23 Oct 2026
EpiSEM-Bench is an executable benchmark of 300 matched unsafe/safe task pairs across six domains. It tests whether tool-using LLM agents take prohibited actions when a tool response omits a safety-relevant fact, even though the request is benign and all returned statements are true. It finds large variation across ten models, and recovery access cuts unsafe execution for all ten.
LLM
EpiSEM-BencharXiv
evals, ai-safety, agentsΒ· Added 24 Oct 2026, published 22 Oct 2026
This paper studies reverse sycophancy: whether users bend toward a confident, consistent, wrong LLM. In a within-subjects experiment, 32 participants learned science topics from five GPT-5-mini assistants with 0 to 100% of facts replaced by falsehoods. Scores fell from 7.4 to 2.9 out of 10, planted falsehoods were chosen on 60% of falsified items against 11% of correctly taught ones, and confidence stopped tracking correctness. It introduces a baseline-corrected Human Deference Index.
LLM
GPT-5-miniarXiv
research, ai-safety, evalsΒ· Added 24 Oct 2026, published 22 Oct 2026
This paper studies evidence-grounded health summarization for menstrual health monitoring. It combines structured evidence conditioning with RAG in a prompt-based constrained generation framework, and scores 4,500 summaries from three LLMs with NLI, atomic factuality metrics and readability measures. Grounding constraints improved uncertainty preservation and generally kept or improved faithfulness against retrieved evidence, while omission effects varied by model. Clinical alignment came with harder reading and more medical terminology.
LLMRAG
arXiv
research, evals, llm-appsΒ· Added 24 Oct 2026, published 22 Oct 2026
Protection Is Not One Event is a survey and human-coded evidence map of 118 RAG defense papers, grouped by measured endpoint into a seven-family taxonomy (kappa=0.867 across 32 annotators). It finds that only 17.8% of studies use content disclosure as their primary endpoint, and that most evaluations use general QA data and non-adaptive attacks. In a testbed on Qwen3-8B, an 8-gram guard cut copying to 0.0%, yet a three-query adaptive attacker still recovered 48.3% of hidden facts. Taxonomy, dataset, coding protocols and testbed are released.
RAGLLMQwen3
Qwen3-8BarXiv
research, evals, llm-appsΒ· Added 24 Oct 2026, published 21 Oct 2026
Survey and human-coded evidence map of 118 RAG defense papers, organized by measured endpoint across a seven-family taxonomy (content disclosure, formal privacy proxies, access control, corpus-use detection, pipeline integrity). Only 17.8% of studies use disclosure or reconstruction as the primary endpoint, and most use non-adaptive attacks on general QA data. A testbed shows a normalized 8-gram guard cuts 20-token copying to 0.0%, yet a three-query adaptive attacker recovers 48.3% of hidden facts on Qwen3-8B.
QwenLLM
prompt injection
AI SecurityΒ· Added 24 Oct 2026, published 21 Oct 2026
Sage-A1.5 is a 35B Mixture-of-Experts agentic model that builds on Sage-A1 for long-horizon problem solving. It adds three capabilities: orchestration with parallel subagents in isolated contexts, verification through progress checking, evidence validation and strategy revision, and open scientific discovery with inspectable research artifacts. The report shows them on complex agentic tasks and multidisciplinary science applications. The page gives only the abstract, no benchmark numbers.
Mixture of ExpertsLLM
Sage-A1.5Sage-A1arXiv
research, agents, modelsΒ· Added 22 Oct 2026, published 20 Oct 2026
"Is Sycophancy a Form of In-Context Updating?" argues that factual sycophancy, a model's deference to a user's false beliefs, is a failure of in-context updating rather than only a bid for approval. Models also revise answers for claims attributed to external sources, more so when better supported, and deference persists when no user approval is at stake. The internal components behind deference also matter causally for general updating, so reducing sycophancy may reduce useful updating.
LLM
arXiv
research, ai-safetyΒ· Added 22 Oct 2026, published 20 Oct 2026
OpenVLHarness is a multimodal reasoning harness for MLLMs built on a capability layer (task-level tool interfaces plus evidence rendering) and persistent multimodal memory that stores images, structured data and web references as addressable artifacts. A coding interface runs generated programs over stored data. Across 22 benchmarks and eight backbones it adds 9.7-12.6 points over no-tool baselines, and GPT-6 Luna at medium effort beats Codex and Visual Sketchpad at maximum effort using at most 37% of their tokens.
vision-language modelQwen3-VLCodex+1
OpenVLHarnessKimi K3GPT-6 Astra+3
agents, multimodal, researchΒ· Added 21 Oct 2026, published 19 Oct 2026
The paper analyses DeepDistinguisher, a transformer-like model that tells Goppa codes apart from random linear codes. Saliency maps and attention visualisation reveal a low-weight-row artifact in the random training instances that the model partly relies on. A pairwise-XOR rule inspired by minimum distance correlates strongly with the model's predictions, and the model loses most of its power on random matrices meeting both constraints. This suggests it exploits general combinatorial properties, not hidden algebraic structure.
Transformer
DeepDistinguisher
researchΒ· Added 20 Oct 2026, published 19 Oct 2026
Analysis of DeepDistinguisher, a transformer model that tells Goppa codes from random linear codes. Using saliency maps and attention visualization, the authors find a low-weight-row artifact in the random training instances that the model partly uses. They propose a pairwise-XOR rule on generator matrix rows that correlates strongly with the model's predictions. On random matrices meeting the minimum distance and XOR constraints, the model loses most of its accuracy, so it exploits general combinatorial properties rather than hidden algebraic structure.
huggingface.copaperπ§ AI
