CompanyAnthropic8 recent entries15 Oct 2026CWE-bench: Refocusing Agentic Security from Exploitation to DefensearXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An a→15 Oct 2026Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environmentsarXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is i
CompanyOpenAI8 recent entries9 Oct 2026From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security IncidentsarXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths →9 Oct 2026Arbiter: Detecting Interference in LLM Agent System PromptsarXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c→15 Oct 2026UDHRBench: Benchmarking Human Rights in Large Language ModelsarXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally r→15 Oct 2026LLMRec: Benchmarking Large Language Models on Recommendation TaskarXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilit→15 Oct 2026EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated ResponsesarXiv:2501.06597v1 Announce Type: cross Abstract: The widespread adoption of generative AI has generated diverse opinions, with individuals expressing both support and criticism of its applications. T→15 Oct 2026CWE-bench: Refocusing Agentic Security from Exploitation to DefensearXiv:2610.17020v1 Announce Type: cross Abstract: Cybersecurity evaluations of AI agents have focused largely on offense, yet a working exploit does not show that an agent can make software safe. An a→15 Oct 2026Assessing and Refining ChatGPT's Performance in Identifying Targeting and Inappropriate Language: A Comparative StudyarXiv:2505.21710v2 Announce Type: replace Abstract: This study evaluates the effectiveness of ChatGPT, an advanced AI model for natural language processing, in identifying targeting and inappropriate →15 Oct 2026A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider constructionarXiv:2510.12306v4 Announce Type: replace Abstract: As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic
CompanyGoogle8 recent entries15 Oct 2026UDHRBench: Benchmarking Human Rights in Large Language ModelsarXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally r→15 Oct 2026REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-TeamingarXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming→15 Oct 2026MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken DialoguearXiv:2610.20172v1 Announce Type: cross Abstract: Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel w→15 Oct 2026Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic EvaluationarXiv:2610.15750v1 Announce Type: new Abstract: Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial →15 Oct 2026Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and BengaliarXiv:2610.19003v1 Announce Type: new Abstract: Abstractive summarization remains challenging across languages, where linguistic quality and factual consistency may diverge, particularly in low-resour→15 Oct 2026Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for LeanarXiv:2610.17331v1 Announce Type: new Abstract: General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. Thi→15 Oct 2026Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question AnsweringarXiv:2610.20085v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) has shown strong effectiveness for text-based LLMs and LLM systems, but its application to audio-visual understand→15 Oct 2026Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian LanguagesarXiv:2610.20263v1 Announce Type: new Abstract: Every multilingual speech pipeline begins with a language decision, an error there propagates silently through recognition, translation and routing. In
CompanyMeta8 recent entries15 Oct 2026Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal StatesarXiv:2607.11414v2 Announce Type: replace Abstract: Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite s→15 Oct 2026CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation ObjectivesarXiv:2610.16876v1 Announce Type: new Abstract: Target-aware multimodal instruction selection requires useful examples and an appropriate balance of supervision. Sample-level rankings can overrepresen→15 Oct 2026ClawLoop: Self-Improving Agents via Harness-Native Training LooparXiv:2610.14118v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents op→15 Oct 2026Choosing LLMs for Strategic Agent InteractionsarXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capabili→15 Oct 2026Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping ResearcharXiv:2609.35089v2 Announce Type: replace Abstract: Meta-analysis is the synthesis of information from multiple sources to arrive at an overarching conclusion. There is a large need for meta-analysis →15 Oct 2026Beyond Size: How Gradients Shape Pruning Decisions in Large Language ModelsarXiv:2311.04902v3 Announce Type: replace Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting per→15 Oct 2026AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian ComputationarXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manne→15 Oct 2026Actionable Meta-Requirements for AI Robustness AuditingarXiv:2610.14356v1 Announce Type: new Abstract: AI-enabled systems must remain dependable when the conditions under which they operate change (e.g., due to input perturbations, distribution shifts, or
CompanyMistral8 recent entries12 Oct 2026CAST: Credit Alignment for Cross-Tokenizer On-Policy DistillationarXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme→14 Oct 2026Lightweight Scheduling Policies for Continuously Batched LLLM Serving Across GPU ArchitecturesarXiv:2610.15899v1 Announce Type: cross Abstract: Large language model serving is increasingly limited not only by model size and GPU speed, but also by scheduling during autoregressive decoding, wher→14 Oct 2026GA-SVD: Generation-aware Singular Value Decomposition for LLM CompressionarXiv:2610.15398v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts →14 Oct 2026From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model EditsarXiv:2610.18098v1 Announce Type: new Abstract: Deleting singular components offers a precise way to remove a capability from a language model, yet the first-order spectral saliency used to rank compo→14 Oct 2026Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete WorksarXiv:2607.09316v2 Announce Type: replace-cross Abstract: Thematic indexing -- the practice of assigning structured conceptual labels to sections of text -- is essential to scholarly access in large-s→15 Oct 2026What Counts as the Same Task? Executable Contracts for Robustness Evaluation of Tool-Using AgentsarXiv:2610.14477v1 Announce Type: cross Abstract: Robustness tests for tool-using agents often change the agent's environment, for example by hiding a hostile note in an invoice, and then judge the ag→15 Oct 2026The Sharp Directions Are Against You: Curvature Analysis of Activation SteeringarXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for b→15 Oct 2026AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RANarXiv:2610.15995v1 Announce Type: cross Abstract: This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Netw
CompanyxAI8 recent entries12 Oct 2026Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based ValidationarXiv:2610.12703v1 Announce Type: cross Abstract: High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation a→14 Oct 2026XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement LearningarXiv:2610.16478v1 Announce Type: cross Abstract: Deep reinforcement learning has shown strong potential for vision-based autonomous driving, but policies trained in simulation often suffer severe per→14 Oct 2026Siam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking SignalsarXiv:2610.15351v1 Announce Type: new Abstract: Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the ne→14 Oct 2026Integrating Feature Understandability into Feature Selection for Human-Centred Tabular ExplanationsarXiv:2610.16627v1 Announce Type: cross Abstract: Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable ins→14 Oct 2026BrainAid: Efficient Brain Tumor Detection Using Lightweight CNNs and Explainable AI for Resource-Constrained EnvironmentsarXiv:2610.15077v1 Announce Type: new Abstract: A brain tumor is an unusual growth of cells in the brain that can be cancerous or not, affecting normal brain function and causing serious risk to healt→15 Oct 2026UDHRBench: Benchmarking Human Rights in Large Language ModelsarXiv:2610.15179v1 Announce Type: cross Abstract: Large language models are increasingly deployed in contexts requiring adherence to ethical and legal norms, yet their alignment with internationally r→15 Oct 2026REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-TeamingarXiv:2610.15513v1 Announce Type: cross Abstract: Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming→15 Oct 2026Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environmentsarXiv:2610.15153v1 Announce Type: new Abstract: We ask whether a tool-using agent whose sole duty is to keep humans alive can be induced, by delayed prompt injection, to kill. The keep-alive duty is i
CompanyDeepSeek8 recent entries15 Oct 2026Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided MitigationarXiv:2610.17763v1 Announce Type: new Abstract: Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and→15 Oct 2026Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicinearXiv:2610.14705v1 Announce Type: cross Abstract: Large language models have advanced medical reasoning, but clinically grounded reasoning in traditional Chinese medicine (TCM) remains challenging bec→15 Oct 2026From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat IntelligencearXiv:2610.20417v1 Announce Type: new Abstract: Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures ac→15 Oct 2026From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMsarXiv:2606.17648v3 Announce Type: replace Abstract: Standard accuracy metrics cannot explain why LLMs handle variable tracking but fail on semantically equivalent loops. We study an internal lifecycle→15 Oct 2026Beyond Size: How Gradients Shape Pruning Decisions in Large Language ModelsarXiv:2311.04902v3 Announce Type: replace Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting per→15 Oct 2026Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based LearningarXiv:2610.14877v1 Announce Type: new Abstract: Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing me→15 Oct 2026AtomSearch: Evidence-Grounded Tree Search for Agent Skill OptimizationarXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin→15 Oct 2026A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software EvolutionarXiv:2610.15765v1 Announce Type: cross Abstract: Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designe
CompanyNVIDIA8 recent entries14 Oct 2026SidewalkBench: Benchmarking Visual Navigation on Urban SidewalksarXiv:2606.16953v2 Announce Type: replace Abstract: Urban sidewalk navigation presents significant challenges due to complex structural layouts, dynamic pedestrian behaviors, and long distances. While→14 Oct 2026Real-Time Traffic Density Estimation: A Hybrid Computer Vision and Predictive Machine Learning PipelinearXiv:2610.14326v1 Announce Type: new Abstract: Traffic density estimation from camera feeds requires connecting visual perception with short-horizon forecasting. We present a two-stage pipeline that →14 Oct 2026Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language ModelsarXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons→14 Oct 2026Embodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic ManipulationarXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded →14 Oct 2026CAST: Real-Time Motion Capture for Any Skeleton TopologyarXiv:2610.14856v1 Announce Type: new Abstract: This paper studies the problem of recovering motion from monocular video, even when the target skeleton topology differs from the subject observed in th→14 Oct 2026AUGUstus: Autonomous Driving VLA Model with Unified Generation and UnderstandingarXiv:2610.16985v1 Announce Type: new Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in →15 Oct 2026Beyond Corrected Actions: Training LLM Agents on Textual CritiquesarXiv:2610.19367v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequ→15 Oct 2026AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge PretrainingarXiv:2610.20086v1 Announce Type: new Abstract: Synthetic data is increasingly used in language-model pretraining. Existing knowledge-corpus synthesis pipelines, including WRAP and Nemotron-CC, usuall