62 results for “Augment”

List Grid

What you seeeverything

Recent Oldest Added A–Z

All types62 Papers50 Articles7 Repos2 Write-ups2 Threads1

“Augment”

arxiv.orgpaper🧠 AI

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

x.compaper🛡️ Security

Cryptography and Security Papers (@FSFG) on X

PrivacyEvalClaw is a tool-augmented deliberative agent that audits privacy leakage in LLM jailbreak responses. The paper is by Krishna Kanth Nakka and co-authors, and it was accepted to AACL-IJCNLP 2026 (arXiv 2610.36711, cs.CR). The tweet gives only the title, authors and venue, so the method and results are not described.

LLM

PrivacyEvalClaw

AI Security· Added 30 Oct 2026, published 29 Oct 2026

x.compaper🧠 AI

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🧠 AI

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🧠 AI

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🧠 AI

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🧠 AI

HerHealthGPT: An Evidence-Grounded Conversational AI System for Women's Reproductive Health Copy title

HerHealthGPT is a conversational AI system for women's reproductive health that combines retrieval-augmented generation, context-aware clarification and source validation in a web interface. Evidence retrieval raises concern-category accuracy from 54.1% to 59.3% over fine-tuning alone on 540 messages from 90 cases. The clarification router reaches 85.6% recall and 86.2% specificity. In a 30-adult study, 83.3% preferred the retrieval-enabled version. The authors say clinical validation is still needed.

RAGLLM

HerHealthGPTarXiv

research, llm-apps· Added 27 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🧠 AI

TriageRAG: Failure-Aware Self-Training for Adapting Retrieval-Augmented Language Models to Specialized Domains

TriageRAG is a failure-aware self-training method for adapting retrieval-augmented LLMs to specialized domains using only an unlabeled corpus. It probes the student on self-generated questions with and without retrieved context, sorts them into known, solved, context-failure and retrieval-failure, and routes each to a matching training signal. With Qwen3-4B on 11 datasets it beats budget-matched SimRAG by 1.2-6.4 points and recovers closed-book accuracy where retrieval hurts.

RAGLLMQwen3

TriageRAGSimRAGCS-Bench+1

research, llm-apps, training· Added 27 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🧠 AI

4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents

4DMemory is a benchmark suite for long-horizon spatiotemporal memory: the LongVideo dataset (about 900 hours of video, over 5,000 manually reviewed questions) and 4DMemoryBench. It also presents the 4DMemory Harness, combining four skills, 22+ tool models and a model-specific RAG system. Across 13 models, the harness improved every one by over 50%, and the same models scored over 10% lower than on a previous benchmark.

RAG

4DMemory4DMemoryBenchLongVideo+2

evals, multimodal, agents· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🧠 AI

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions

This paper describes an evidence-aware retrieval evaluation protocol for a clinical RAG system over breast lesion management literature. Relevance is defined by evidence spans mapped to all containing chunks. A hybrid retriever (dense, BM25, cross-encoder reranking) with 384-token chunks and 20% overlap reached 0.94 Recall@3 on 18 queries. Expanding ground truth from 25 to 37 spans did not change rankings. The authors note the small set needs independent validation.

RAGBM25LLM

DeepSeekDeepEvalarXiv

llm-apps, evals, research· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

Every Part Has Its Role: Part-of-Speech Effects in LLM Post-Training

Every Part Has Its Role studies concept augmentation in LLM post-training, where a target word is replaced by related alternatives in training sentences. It extends prior work from nouns to verbs and adjectives. Concept augmentation improves perplexity most consistently on news regardless of part of speech, while verbs give the most reliable downstream gains. CKA and linear probing show the largest gains do not match the largest representation changes.

LLM

arXiv

research, training· Added 23 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🧠 AI

Can It Actually Work? Synthesizing Functional CAD Mechanisms

FunCAD-Harness is a framework in which LLM agents design CAD mechanisms and revise them using physical simulation feedback. It turns abstract functional requirements into candidate-specific physical tests. The paper also introduces FunCADBench, a benchmark of 46 mechanism families with interdependent, multi-step operations. Experiments on frontier LLM agents show it exposes mechanical failures that visual inspection misses and raises functional success over standard simulation-augmented baselines.

LLM

FunCAD-HarnessFunCADBencharXiv

research, evals, agents· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition

EpiLens is a lightweight, open-source retrieval-augmented generation package that applies a fixed retrieval template and output schema to every paper in a corpus and links outputs to source passages. On a corpus of 2,297 epidemiology papers, its classifier matches or exceeds supervised and zero-shot baselines on four tasks without task-specific training data, scored against 214 manual labels. It also compares model-based study shares across parameters and pathogens.

RAGLLM

EpiLensSARS-CoV-2mpox+1

llm-apps, research· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

E-Layout: Layout-Stage Logic Restructuring via RL-Optimized Equality-Saturated Graph Retrieval-Augmented Generation

E-Layout is an ML-driven framework for post-placement logic restructuring in IC physical design. It builds equivalent logic alternatives with e-graph equality saturation, links logic choice to physical realization through a graph-based RAG model, and refines the choices with reinforcement learning on design-level timing feedback. On 9 designs it gives about 6% TNS and 2% WNS improvement and 1% less area than a commercial physical design flow.

RAG

E-LayoutarXiv

research· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

Large-Scale Biomedical RAG: Corpus Scaling, Document Representation, and Efficiency Trade-offs

This paper is a controlled, large-scale evaluation of biomedical Retrieval-Augmented Generation across growing corpus sizes. It compares abstract, flat full-text and hierarchical full-text representations, with and without reranking, on multiple-choice QA over five external benchmarks and a held-out test set. RAG gave mean gains of up to 9.6 points externally and 10.2-30.3 points on the held-out set. Hierarchical indexing used 67% fewer units and 44-56% less storage than flat full-text.

RAG

arXiv

research, llm-apps, evals· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🛡️ Security

RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation

RAGLeak is a supply-chain privacy backdoor attack on retrieval-augmented generation. When triggered, the backdoored generator reversibly obfuscates retrieved private documents, and an auxiliary LLM recovers them. Tested on three model families and three domains, it reaches up to 100% attack success rate, loses at most 10 points under detection-based defenses, and survives clean fine-tuning and changes of model scale and version. Source code is released.

LLM

RAGLeak

AI Security, Supply Chain· Added 21 Oct 2026, published 19 Oct 2026

mercor.comarticle🧠 AI

90% of US working hours are spent on tasks not covered well by AI benchmarks

Mercor's Benchmark Map tags prompts from 29 selected AI benchmarks to O*NET tasks with an LLM judge, following Wang et al. It covers 923 occupations and 18,797 tasks. It finds only 208 occupations have a task with at least 5 benchmark prompts, and about 90% of US working hours fall on tasks with little or no benchmark coverage. Coverage skews toward AI-exposed, high-wage-bill, high-importance tasks such as software engineering and law, and it leaves out smaller middle-income knowledge work and physical work. The page also tests O*NET-weighted occupation scores on the APEX benchmarks for four occupations, and lists the limits of the method: sparse items, saturation, quality weighting, and augmentation versus automation.

LLM

MercorAPEXO*NET+6

evals, ai-policy· Added 17 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning

ThetreStageAI is a retrieval-augmented framework for structured Bengali theatre production planning. It keeps separate scene, actor-blocking and lighting views, embeds Bengali text with BGE-M3, indexes it in view-specific Qdrant collections, and has Gemini generate schema-constrained JSON, with validation and at most one repair attempt. The authors build a synthetic dataset of 500 records (1,500 retrieval documents) and compare single-combined retrieval with multi-view retrieval. Code and data are public.

RAGGeminiBGE-M3+1

ThetreStageAI

llm-apps, research· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

Enhancing RAG-based Medical VQA with Gated Multimodal Representations

This paper presents a multimodal retrieval-augmented generation framework for Medical Visual Question Answering. A Gated Multimodal Unit learns a joint query representation from the medical image and the clinical question, so evidence retrieval uses both modalities while the Med-LVLM stays frozen. On benchmark datasets it consistently beats a reference Med-LVLM and stays competitive with state-of-the-art methods. The page gives no dataset names or numbers.

RAGvision-language model

arXiv

research, llm-apps, multimodal· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

Private Retrieval Augmented Generation via Random Projection

Proposes protecting the retrieval datastore in RAG systems by applying the same random projection to datastore embeddings and query embeddings. This provably preserves query-item semantic similarity while substantially mitigating data extraction attacks. Across multiple RAG architectures and datasets it beats prior differential-privacy-based methods on retrieval and generation quality, with comparable empirical privacy under strong attacks, making it a practical baseline for privacy-preserving RAG.

RAGLLM

arXiv

research, llm-apps· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🛡️ Security

Private Retrieval Augmented Generation via Random Projection

Proposes applying the same random projection to both datastore embeddings and query embeddings in RAG systems. The authors claim this provably preserves query-to-item semantic similarity while substantially mitigating datastore data-extraction attacks. Across several RAG architectures and datasets it reportedly beats prior differential-privacy-based defenses on retrieval and generation quality, with comparable empirical privacy under strong attack models. It is presented as a lightweight baseline for privacy-preserving RAG.

LLM

differential privacydata extraction attacks

AI Security· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

Proposes SCOPED (Skill-Decoupled On-Policy Expert Distillation), which trains capability-specific RL experts for vision-language models. It extracts explicit skills from them through reward-guided reflection. During on-policy distillation the skills guide expert supervision but are hidden from the unified student, so the student internalizes the procedural knowledge and needs no explicit skills at inference. Across eight multimodal benchmarks it beats the backbone and mixed-capability RL. Analyses show cross-capability gradient interference in joint RL, and that skill augmentation gives more consistent expert trajectories, more attention to task-relevant visual evidence, and better preservation of expertise.

vision-language model

SCOPEDarXiv

research, training, multimodal· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning

Legal-R1 is an agentic retrieval framework for evidence-based legal question answering that splits reasoning across three agents. A Lawyer agent decides when to retrieve, which legal source to query, what evidence to seek and when it has enough. A Legal Assistant retrieves statutes and precedent cases with authority-aware and diversity-aware selection, and a Judge agent writes the final answer from the full evidence trajectory. Only the Lawyer agent is post-trained, using masked supervised fine-tuning and trajectory-aware reinforcement learning. The paper reports gains over general-purpose, legal-specific and retrieval-augmented baselines on several Chinese legal benchmarks.

RAG

Legal-R1arXiv

research, agents, llm-apps· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models

This paper shows that vision-language-action (VLA) models are highly sensitive to how instructions are phrased: a single-word change (e.g. "stove" vs "hot plate") can shift task success by dozens of points on π0 and π0.5 checkpoints in the LIBERO benchmark, even after rephrase-augmentation finetuning. The authors characterize this with statistically tested single-edit swings and an oracle phrase search, then mitigate it without retraining by having an LLM distill scoring evidence into 10-20 explicit rephrasing rules that rewrite incoming instructions at deployment time, improving frozen π0 by 16-27% relative on held-out tasks and lifting π0.5's in-finetune success from 93.6% to 97.8%.

vision-language model

π0π0.5LIBERO

research, multimodal· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing

RECAST (Routing Evidence through Computation, Access, and Synthesized Tools) reframes retrieval-augmented generation as a sequential decision process: a lightweight RouterLM iteratively selects or formulates primitive/custom operations, a frozen CompilerLM turns custom operations into executable code, and a frozen AnswerLM produces the final answer once evidence is judged sufficient. RouterLM is trained with supervised fine-tuning followed by GRPO, and the system reaches a 75.6% mean success rate across six heterogeneous benchmark families, beating the strongest large-model baseline by 15.9% and a training-free Gemini 3.5 Flash router by 5.0%, with strong zero-shot generalization on three held-out benchmarks. It targets tasks where evidence must be derived through filtering, aggregation, or computation across multiple sources rather than retrieved verbatim.

Qwen3.5GeminiGRPO

Gemini 3.5 Flash

llm-apps, training, research· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

Self-correction Optimization for Interleaved Multimodal Generation

This paper introduces Self-Correction Optimization (SCO), a training-free method that improves consistency in interleaved image-text generation from multimodal large language models. SCO treats the classifier-free guidance update as a reference signal and applies minimal corrections under two constraints—a new-event constraint for temporal consistency and a state-preserving constraint for visual-subject coherence—avoiding the computational cost of additional training with augmented data. The authors show improvements on interleaved multimodal generation benchmarks and extend the method to video generation tasks like robot manipulation and long-horizon handcrafting.

vision-language model

research, multimodal· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora

This paper runs a mechanism-isolating ablation of four document-structure treatments used in retrieval-augmented generation — structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval — under one protocol with matched chunk sizes and a semantically null placebo (shuffled heading paths) to control for the confound that any prepended text perturbs embeddings. Using a coverage-aware nDCG metric and document-clustered bootstrap with Holm correction across 200 Wikipedia Featured Articles (951 queries) and 1,585 QASPER papers (4,303 questions), it finds that structure-aligned chunking with real heading paths beats both contextualized fixed windows and the placebo, naive hierarchical retrieval hurts performance (traced to first-stage section recall failures), and gold structure beats LLM-induced structure on Wikipedia but not QASPER. Effect sizes are small but statistically significant and consistent across corpora, giving RAG practitioners evidence-based guidance on which structure-aware retrieval tricks actually help versus which are placebo effects.

QASPERWikipedia Featured Articles

research, llm-apps· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented Generation

EntroPrefill proposes a Renyi-entropy-guided mechanism for pruning context mid-prefill in retrieval-augmented generation, using sink-isolated regularized head pooling compatible with grouped-query attention to decide which tokens can be safely discarded. It derives a mixture-to-head deletion envelope bounding feasible token removal, a finite-sample observer guarantee valid under adaptive layer selection, and a conditional transformer perturbation bound with explicit Lipschitz constants and a first-token decision-margin corollary, plus a systems-level break-even analysis of KV-transfer payload versus pruning savings. The paper is explicitly theoretical, defining assumptions and formal limits without reporting empirical speedup or accuracy-preservation results.

Transformer

llm-apps, research· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

EC-RAG (Event Chain Retrieval-Augmented Generation) is a training-free framework for long-video question answering that organizes video content into an explicit, temporally ordered "event chain" instead of retrieving isolated frames or snippets. It partitions video into semantically coherent segments, fuses multi-modal signals (speech, text, visual cues) at the event level, and retrieves relevant events from the chain to answer queries, working as a plug-and-play addition to existing large video-language models (LVLMs) without extra training. Evaluated on Video-MME, MLVU, and LongVideoBench, it outperforms frame-level retrieval baselines, showing the value of modeling temporal/event structure for long-video understanding.

vision-language model

Video-MMEMLVULongVideoBench

research, multimodal, llm-apps· Added 7 Oct 2026, published 6 Oct 2026

arxiv.orgpaper🛡️ Security

RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems

RAG-PIBench is a benchmark of 4,876 contextual examples for evaluating prompt-injection detectors embedded in retrieved content within Retrieval-Augmented Generation (RAG) systems. The authors use a leakage-aware construction pipeline with frozen train/validation/protected-test splits and compare keyword-based, semantic-reference, TF-IDF, and transformer-based detectors, finding DistilBERT achieves the best protected-test performance (F1 = 0.896, PR-AUC = 0.968) while TF-IDF with SVM or logistic regression remains competitive. It highlights the risk that naive benchmark construction can leak information between splits, inflating reported detector performance for RAG prompt-injection defenses.

DistilBERTTF-IDF

RAG-PIBench

AI Security· Added 7 Oct 2026, published 6 Oct 2026

github.blogarticle🧠 AI

ReviewBench: An open benchmark for AI code review

ReviewBench is an open benchmark from GitHub and Microsoft for evaluating AI code review agents, built from 219 pull requests drawn from 187 public repositories across 19 languages, modeled on the distribution of 103.9 million real GitHub pull requests. It uses a three-stage multi-source golden-set process, reports six precision/recall-family metrics (including grounded and augmented recall to credit issues beyond the fixed golden set), supports severity/category slicing and a configurable F-beta score, and was validated by independent senior engineers who agreed with its labels 96.6 percent of the time. GitHub used it to evaluate Copilot code review (CCR), showing its offline predictions tracked the direction of later production A/B results.

GitHub CopilotGitHub

ReviewBenchMicrosoftMichelle Zhou

evals, coding-agents· Added 8 Oct 2026, published 5 Oct 2026

arxiv.orgpaper🧠 AI

AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation

This paper proposes AI-decision checkpoints, explicit moments in business process development where process developers must evaluate whether to adopt, constrain, or reject AI-candidate sub-processes built with LLMs, RAG, or AI agents, based on expected effects on time, cost, quality, flexibility, and legal or organisational constraints. The checkpoints are embedded in a six-module BPM teaching lifecycle covering process modeling, simulation, workflow execution with AI agents, and process mining, piloted via a fictitious customer-onboarding teaching case with formative observations drawn from instructor logs and student artifacts. It addresses a curriculum gap where AI is still treated as a bolt-on rather than a first-class design element in BPM education.

ai-policy· Added 6 Oct 2026, published 5 Oct 2026

arxiv.orgpaper🧠 AI

World Embedding Benchmark

The World Embedding Benchmark is a new evaluation suite of 8,000 controlled simulation cases across 80 families (fluid mechanics, solid mechanics, dynamics, optics & electromagnetism), each pairing a rendered video with simulation-derived physical annotations. It tests pre-trained omnimodal embedding models on text-video retrieval, physical-property regression, and multiple-choice video-description classification, finding that current embeddings align poorly cross-modally while lightweight probes can still recover physical quantities, and that continual contrastive training improves alignment but hurts regression. The authors also show retrieval-augmented generation using these embeddings with MiniMax-H3 improves the physical fidelity of generated videos.

MiniMax-H3

World Embedding Benchmark

evals, multimodal, research· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaper🧠 AI

CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation

CLIMB is a training-free, inference-time framework for multimodal retrieval-augmented generation that improves knowledge-intensive visual question answering. It first builds a compact, non-redundant evidence pool using an MMR-style objective balancing query relevance and redundancy, then applies an R/E/C critic (relevance, evidence specificity, cross-modal alignment) alongside a confidence estimator that only accepts an answer update when estimated confidence increases, giving a built-in stopping criterion without modifying the underlying retriever or MLLM. Experiments on Encyclopedic-VQA and InfoSeek show consistent gains over existing multimodal RAG baselines.

vision-language model

Encyclopedic-VQAInfoSeekCLIMB

llm-apps, multimodal· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaper🧠 AI

Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation

This paper studies whether forcing an LLM to reason in a specific language helps or hurts accuracy in retrieval-augmented generation (RAG), extending prior findings from short-prompt reasoning to settings where the model must integrate large retrieved context. The authors build a fully monolingual German RAG QA benchmark set in the fictional world of the tabletop RPG "The Dark Eye" — a domain richly documented in German but too niche for the model to answer from memory — forcing retrieval rather than memorization. They find that aligning reasoning language with the query/document language (German) outperforms a mismatched but higher-proficiency language (French), showing the benefit comes from language alignment rather than raw language skill, though forced German reasoning still only matches, and never exceeds, the model's native unconstrained English reasoning. The testbed and QA benchmark are publicly released.

Mario Sanz-GuerreroThe Dark Eye

research, llm-apps· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaper🧠 AI

UniWAM: Unified World-Action Model

UniWAM is a unified architecture that combines a physical reasoner, a world generator, and an action predictor to jointly learn semantic understanding, visual generation, and action prediction for embodied agents, bridging vision-language-action (VLA) models and world-action models. It uses a data cleaning/annotation pipeline for human egocentric and robot data, represents low-level actions in natural language for VQA/egocentric/robot co-training, and introduces future visual noise augmentation plus history-conditioned flow matching to cut denoising steps while achieving state-of-the-art results on in-distribution performance, robustness, generalization, instruction following, and long-horizon tasks. The paper also reports a log-linear scaling law for unified human-robot co-training.

vision-language modelflow matching

UniWAM

research, multimodal· Added 2 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🧠 AI

Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning

This arXiv survey organizes recent Retrieval-Augmented Generation (RAG) research into a four-axis taxonomy covering retrieval efficiency, robustness/security, user-driven interactivity, and multi-step reasoning. It formalizes RAG framework components, reviews dense/sparse retrieval, fusion strategies, embedding optimization, and RL-based retrieval policies, and compares Naive, Advanced, and Modular RAG architectural variants alongside evaluation practices and domain applications. The paper closes by outlining open challenges in retrieval quality, reliability, domain adaptation, scalability, and explainability.

Retrieval-Augmented Generation

llm-apps, research· Added 2 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🛡️ Security

Walking the Embedding Space: Datastore Extraction from Multimodal RAG

Researchers introduce ImmRAG, a black-box data extraction attack against image-returning Multimodal Retrieval-Augmented Generation (MRAG) systems, where the retrieved image itself is the model's response. Instead of malicious text prompts, ImmRAG embeds attack instructions inside an attacker-supplied image and uses relevance-weighted resampling to steer queries toward unexplored regions of the embedding space, progressively reconstructing more of the private datastore. Tested against CLIP-family retrievers across medical, document, and general-purpose scenarios, a single 2500-query run reconstructed up to 611 radiology images, 566 document scans, and 416 general images — up to 5.6x more distinct items than a non-adaptive baseline — highlighting the lack of safeguards against multimodal data leakage.

CLIP

ImmRAG

AI Security· Added 2 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🧠 AI

A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering

MatRAG is a hierarchical Retrieval-Augmented Generation framework for multi-hop question answering that organizes a document corpus into a Directed Acyclic Graph of clusters with progressively coarser granularity, indexing each level with a correspondingly lower Matryoshka embedding dimension. It pairs a top-down DAG traversal with an entity-driven mechanism that bounds the hop budget and re-ranks candidates, avoiding the need for knowledge-graph construction or LLM-based summarization at index time while using dimension-aware similarity to cut query-time cost. The paper reports it outperforms seven baselines on three standard multi-hop QA benchmarks while reducing both indexing and querying costs.

Matryoshka Representation Learning

MatRAG

llm-apps· Added 2 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🧠 AI

Semifactual Credit-Augmented Policy Optimization

This paper proposes Semifactual Credit-Augmented Policy Optimization (SCAPO), a variant of Group Relative Policy Optimization (GRPO) for reinforcement learning with verifiable rewards (RLVR). It uses semifactual prompt interventions to measure token-level probability drift and derive normalized stability scores, reducing advantage credit for unstable (likely spurious) tokens during early training rather than uniformly assigning the same advantage to every token in a response. On Qwen3-4B-Base and Qwen3-1.7B-Base, SCAPO improves AIME 2024-2026 accuracy over GRPO by 5.63 and 4.17 percentage points respectively, and achieves the best results on most math benchmarks and all out-of-distribution benchmarks tested.

GRPOQwen3

Qwen3-4B-BaseQwen3-1.7B-BaseAIME

training, research· Added 1 Oct 2026, published 30 Sep 2026

arxiv.orgpaper🧠 AI

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

This paper introduces Grounded Entity Biographies (GEB), a long-video memory framework that links visually grounded observations of the same physical object or person across clips into retrievable "biographies," addressing the problem of text-derived entity descriptions failing to resolve physical identity across hours- or days-long recordings. During question answering, these biographies are retrieved alongside episodic evidence so a model can follow an entity through events via identity links established at memory-construction time. Evaluated on four long-video QA benchmarks (day-long and week-long recordings), GEB improves over prior memory frameworks, reaching 72.0% accuracy on EgoLifeQA — 4.4 points above the prior best published result — with ablations showing both grounded identity association and biography reading contribute to the gains.

EgoLifeQA

research, multimodal· Added 30 Sep 2026, published 29 Sep 2026

arxiv.orgpaper🧠 AI

FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation

FracGen is a fracture-aware video generation model that, given a single image of an intact object, generates plausible and controllable fracture dynamics (where an object tears, crack propagation speed, pre-failure deformation) conditioned on physics signals. It is trained using FracSim, a material point method (MPM) simulation framework augmented with a continuum damage model that produces paired fracture videos and dense pixel-aligned physical fields at no extra rendering cost; FracGen jointly predicts these fields alongside RGB video and is supervised with physics-informed consistency losses. The authors also introduce a benchmark for evaluating physical plausibility of generated fracture video, showing FracGen outperforms existing video generation baselines in both physical and visual fidelity.

material point method

FracGenFracSim

research, multimodal· Added 30 Sep 2026, published 29 Sep 2026

arxiv.orgpaper🛡️ Security

PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution Shift

PIDS-Bench is a frozen, multi-axis benchmark for prompt-injection detectors that jointly measures attack detection and benign false-positive rates across in-distribution inputs, hard-benign prompts mimicking injection structure, obfuscated attacks, and domain/structural distribution shifts. Testing seven detectors (learned baselines, external prompt-injection classifiers, broad-safety comparators) plus a rule-based baseline, the authors show a detector with F1 > 0.98 on held-out data still misclassifies roughly one-third of an externally-sourced benign security-adjacent corpus, and that hard-negative augmentation reduces over-defense only on curated stress inputs, not on externally-sourced ones — a pattern they call provenance-sensitive over-defense.

LLM

AI Security· Added 26 Sep 2026

arxiv.orgpaper🧠 AI

Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use

This paper formalizes OpenAgent, a problem setting for evaluating LLM tool-use agents under real-world distributional shifts in queries, actions, observations, and domains. Using a controlled sandbox with a four-tier hierarchy (Perception, Interaction, Reasoning, Internalization) of environmental shifts, the authors show that both SFT- and RL-trained agents degrade significantly outside static training distributions, and propose Perturbation-Augmented Fine-Tuning as a mitigation.

OpenAgentLAMDA-NeSy

agents, research· Added 26 Sep 2026

arxiv.orgpaper🧠 AI

AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs

AgentWorld is a benchmark of 100 human-annotated tasks (plus 100 augmented variants) for evaluating long-horizon multi-agent LLM collaboration in a MMORPG-style sandbox, requiring 3-20 agents with asymmetric roles to coordinate over 50+ interaction rounds without visibility into each other's internal states. The authors introduce Causal Collaboration Effectiveness (CCE), a graph-based metric that traces causal dependencies between agent actions to measure how much of a team's effort actually contributed to task success, beyond simple pass/fail. Testing Gemini 3 Flash, Claude Haiku 4.5, GPT-5 Mini, and DeepSeek R1-70B shows even the best model only reaches 52.0% task success, with failures traced to communication breakdowns, role confusion, and inability to maintain shared plans.

Gemini 3 FlashClaude Haiku 4.5GPT-5 Mini+1

AgentWorldCausal Collaboration Effectiveness

evals, agents· Added 28 Sep 2026, published 25 Sep 2026

arxiv.orgpaper🧠 AI

How Far Can INRs Go? Cross-Domain Parameter-efficient INR-Based Semantic Segmentation for Brain MRI

This paper studies Implicit Neural Representations (INRs) as a lightweight alternative to conventional CNN pipelines (e.g. U-Net) for brain MRI semantic segmentation, analyzing their scaling behavior and cross-domain generalization. The authors find INR-based models excel in low-parameter, limited-augmentation regimes but don't scale as well as U-Net with larger capacity, and that segmentation-relevant information is distributed across multiple INR layers. Building on this, they propose HierINRSeg, a hierarchical multi-layer INR architecture that beats the MetaSeg baseline by 5.6 Dice points in-domain and 8.2 points out-of-domain.

U-Net

HierINRSegMetaSeg

research, multimodal· Added 28 Sep 2026, published 25 Sep 2026

arxiv.orgpaper🧠 AI

To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

VeriSpeak is a new probe benchmark of 3,879 spoken claims (temporal, geographical, relational facts, balanced true/false labels) for evaluating speech-based fact verification in Large Audio Language Models. The paper finds a consistent text-speech modality gap—LALMs that verify written claims well often fail on spoken versions—and shows retrieval alone gives limited gains since models conflate retrieved evidence with the spoken claim, while retrieval combined with explicit reasoning boosts a thinking-tuned LALM to 86.1% accuracy. The dataset is publicly released on Hugging Face.

Hugging Face

VeriSpeak

evals, multimodal, research· Added 26 Sep 2026, published 24 Sep 2026

arxiv.orgpaper🧠 AI

Contrastive Learning for Authorship Verification

This arXiv paper studies authorship verification (determining if two texts share an author) and shows contrastive learning beats a classification-based baseline. The authors ablate loss function, batch size, training duration, pretrained backbone, input context length, and random text span augmentation, then build a ModernBERT bi-encoder that reaches 98.4% accuracy on the PAN21 authorship verification benchmark.

ModernBERT

PAN21

research· Added 24 Sep 2026, published 23 Sep 2026

arxiv.orgpaper🧠 AI

VideoGen-Agent: Reinforcing Video Generation Agents

VideoGen-Agent is a multimodal agent trained with multitask agentic reinforcement learning to coordinate augmentation, generation, and verification tools for video generation, using supervised fine-tuning on teacher trajectories followed by RL with a category-aware hybrid reward. The authors introduce VABench, a 600-prompt held-out benchmark covering procedural knowledge, identity preservation, physical consistency, scene composition, and multi-shot temporal structure, on which the agent improves over its base text-to-video model from 56.5 to 75.6 (and 86.1 when upgrading the underlying generation tools).

VideoGen-AgentVABench

multimodal, agents, research· Added 22 Sep 2026, published 21 Sep 2026

arxiv.orgpaper🧠 AI

Closed-World Resolution Against Tool Hallucination in LLM Agents

This arXiv paper studies tool hallucination in tool-augmented LLM agents, where agents call tools that do not exist or pass arguments no schema declares, arguing existing tool-selection and tool-gating defenses structurally cannot catch it since a hallucinated call was never a decision a gate made. The authors give a five-class taxonomy (H1 to H5), propose the Resolution Rung, a training-free closed-world resolver based on registry membership plus a signature check that must run before any causal gate, and extend the analysis to the Model Context Protocol with a second taxonomy (M1 to M5) covering collisions and shadowing when multiple servers are merged into one namespace. Across ten hosted models they measure 322 hallucinations on two invocation surfaces and 154 on a live MCP surface, and release the versioned Hallucinated-Tools Benchmark for comparing resolvers.

Model Context Protocol

Laxmipriya Ganesh Iyer

mcp, evals· Added 2 Oct 2026, published 16 Sep 2026

arxiv.orgpaper🧠 AI

Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation

This arXiv paper proposes augmenting generated robot manipulation videos with synthesized contact audio, using the loudness of generated sounds to derive a time-varying desired-force profile for contact-rich tasks. The pipeline drives a Franka Panda robot via a closed-loop force regulator tracking the audio-shaped force curve, outperforming kinematic-only video-generation baselines, and doubles as a data-generation engine for training closed-loop manipulation policies.

Franka Panda

Tianyu Li

multimodal, research· Added 22 Sep 2026, published 16 Sep 2026

arxiv.orgpaper🧠 AI

Programmable World Model

Programmable World Model decouples persistent world-state evolution from visual rendering in video world models: an agent compiles natural-language instructions into executable programs governing entity states and transition rules, which a lightweight engine executes and maintains as explicit global state (including off-screen entities and non-visual attributes). State-augmented 3D oriented bounding boxes plus camera trajectory are deterministically compiled into pixel-aligned conditioning signals fed to a pretrained video model that renders the scene, enabling playable games with predefined mechanics and direct entity control. On the paper's new CombatStateBench benchmark it achieves 94% Count Accuracy and 98% State Accuracy, beating existing interactive video world models on long-horizon coherence.

video model

CombatStateBench

research, multimodal, evals· Added 22 Sep 2026, published 9 Sep 2026

snyk.ioarticle🛡️ Security

Symlinks Are Still Scary (And Yes, You Can Commit Them to Git)

Snyk explains the decades-old symlink attack (CWE-61) and the underappreciated fact that Git will happily commit, push, and recreate symlinks (file mode 120000) from a cloned repo, letting an attacker ship a file like project_settings.json that's secretly a pointer to ~/.ssh/authorized_keys. It walks through Wiz Research's "GhostApproval" report, which found that six AI coding agents (Amazon Q Developer, Claude Code, Augment, Cursor, Google Antigravity, Windsurf) can be prompt-injected via README instructions into following such a symlink and writing attacker SSH keys or shell-config payloads before the user ever sees an accurate confirmation dialog (CWE-451, UI misrepresentation). It also recaps prior symlink-driven CVEs (tar npm package CVE-2021-32803, Leaky Vessels CVE-2024-21626, Git submodule CVE-2024-32002) and gives concrete mitigations: canonicalize-then-check-boundary atomically (e.g. openat2 with RESOLVE_BENEATH), show real resolved targets in approval dialogs, and audit repos with `find . -type l` or `git ls-files -s` before trusting them.

GitClaude CodeCursor+3

CVE-2021-32803CVE-2024-21626CVE-2024-32002+6

AI Security, AppSec· Added 3 Sep 2026, published 9 Jul 2026

wiz.iowriteup🛡️ Security

GhostApproval: A Trust Boundary Gap in AI Coding Assistants

Wiz Research discloses GhostApproval, a symlink-following vulnerability (CWE-61) found in six AI coding assistants — Amazon Q Developer, Claude Code, Augment, Cursor, Google Antigravity, and Windsurf — where a malicious repo containing a symlink disguised as a config file tricks the agent into reading/writing sensitive files like ~/.ssh/authorized_keys outside the workspace sandbox. In several tools the agent's internal reasoning correctly identifies the true target file, but the confirmation dialog shown to the user still displays the fake filename (CWE-451, UI misrepresentation), turning human-in-the-loop approval into a rubber stamp; some tools (Amazon Q, Windsurf) even write to disk before the approval prompt appears. AWS (CVE-2026-12958), Google, and Cursor (CVE-2026-50549) shipped fixes; Anthropic initially rejected it as outside threat model before later shipping a symlink warning, Augment acknowledged but hasn't patched, and Windsurf has not responded.

Claude CodeCursorWindsurf+4

GhostApprovalCVE-2026-12958CVE-2026-50549+2

AI Security, AppSec· Added 3 Sep 2026, published 8 Jul 2026

github.comrepo🧠 AI

trailhq/Graft

Graft (npm package @nanonets/graft) builds a local, regenerable code graph from a repo — markdown nodes summarizing subsystems plus a per-symbol tree-sitter wiring graph — and wires it into coding agents like Claude Code, Codex, Cursor and Gemini so they no longer re-explore the codebase from scratch every session. It ships an MCP server, CLI commands (ask/grep/callers/skeleton/map/blast/viz), and Claude Code-specific hooks (statusline, blast-radius warnings, auto-resync). The project reports its own benchmarks: a 162-run internal harness and a 50-instance SWE-bench Verified comparison where graft-augmented Claude Sonnet 5 resolved 33/50 instances vs. 27/50 for cold Claude Code, with fewer tool calls, tokens and wall-clock time.

Model Context ProtocolClaude CodeCodex+11

SWE-bench VerifiedClaude Sonnet 5PocketBase

coding-agents, mcp· Added 30 Sep 2026, published 3 Jul 2026

github.comrepo🛡️ Security

Teycir/SkillsGuard

SkillsGuard is a zero-dependency static security scanner for AI agent skill packages (SKILL.md files and bundled scripts) that detects prompt injection, exfiltration, obfuscated payloads, persistence, and privilege escalation before an agent reads or executes them. It recursively decodes base64/hex/URL-encoded blobs to catch hidden attacks like a base64-wrapped reverse shell, computes a 0-100 risk score, and integrates into CI (SARIF/JSON output), git pre-commit hooks, and Claude via an MCP server (scan_skill tool) or a free hosted Cloudflare Workers API. The README also situates it against competing agent-skill scanners (NVIDIA, Cisco, Snyk, Mondoo, SkillSpector, SkillScan), noting it's the only one requiring no account/API/LLM dependency versus SkillSpector's LLM-augmented semantic analysis backed by a study of 42,447 scanned skills.

Node.jsModel Context ProtocolSARIF+3

SkillSpector

AI Security, DevSecOps· Published and added 21 Jun 2026

endorlabs.comarticle🧠 AI

Endor Labs: AURI Agents

Endor Labs announces AURI Agents, a free catalog of pre-configured security agents (SCA Remediation, AI SAST Triage, Probe Droid, Endor Troubleshooter and six more). They run inside Claude Code, Codex, Cursor and similar hosts, using the user's own LLM keys and git credentials (GitHub via gh, GitLab via glab). The open-source Endor Labs Agent Kit defines each agent as a YAML Source Recipe plus markdown instructions, compiles it into per-host artifacts, and ships a skill that helps users author new agents with eval cases. Endor claims expert agents finish tasks 2.8x faster with 92% fewer tokens than an unaugmented agent. Mutating actions require confirmation and most agents are read-only.

Claude CodeCodexCursor+6

Endor LabsGitLab

coding-agents, agents· Added 10 Oct 2026, published 17 Jun 2026

endorlabs.comarticle🛡️ Security

Endor Labs: AI AppSec Agents Cost 12x More Without Pre-Computed Security Context

Endor Labs argues that AI coding/security agents are far more expensive when they must reconstruct security context (SCA, reachability, license data) from raw repo reads instead of using deterministic tools. Their benchmark of 442 security prompts (reachability, exploitability, prioritization, remediation, license compliance) across 12 open-source projects in 6 languages found an LLM-only agent averaged ~14 tool calls per question (mostly grep/file-read/web-search) versus ~2.5 high-level calls when equipped with Endor Labs' precomputed security data, yielding a 91.7% token reduction and 4.5x fewer tool calls. The piece also cites a naive academic LLM vuln-scan baseline that flagged ~14,000 candidate sinks with zero confirmed vulnerabilities, and quotes Anthropic's Michael Moore stating Claude Code Security is meant to augment, not replace, existing AppSec tooling.

Endor LabsClaude CodeCodex+3

MythosMichael MooreFinOps Foundation+3

AI Security, AppSec· Published and added 11 Jun 2026

aikido.devarticle🛡️ Security

What is AI SAST?

Aikido's explainer draws a line between two things vendors both call "AI SAST": AI-native (reasoning-based) SAST, where an LLM reads source code like a reviewer to trace data flow and catch logic flaws such as IDORs, broken access control and business-logic bypasses that have no syntactic signature; and AI-augmented SAST, where a traditional deterministic rule engine stays the detection core and AI is layered on for triage, false-positive filtering and autofix. It also positions AI SAST against classic pattern-matching SAST (fast, deterministic, runs every commit) and AI pentesting (validates real exploits against a running app, produces proof for audits), arguing organizations need all three at different cadences. The piece closes by mapping Aikido's own Code Security Audit and Deep PR Review products onto the AI-native category.

Aikido Security

IDOR

AppSec, AI Security· Added 3 Sep 2026, published 6 Jun 2026

x.comthread🧠 AI

rohonchain

A detailed X thread walking through applying neural networks (specifically LSTMs) to quantitative trading signal generation, with full PyTorch implementation code. It covers why raw price prediction fails due to non-stationarity, how to engineer stationary features (log returns, volatility ratios, momentum, volume z-scores) validated via Augmented Dickey-Fuller tests, LSTM gating mechanics for sequential market data, rigorous train/validation/test splitting with early stopping, walk-forward validation, and Kelly-criterion position sizing.

PyTorchPythonscikit-learn+2

Two SigmaCitadelRenaissance Technologies+1

training, evals· Added 22 Sep 2026, published 13 May 2026

Showing 60 of 62