CompanyAnthropic8 recent entries12 Oct 2026SWE-Duel: Towards a Self-Scaling Arena for Coding AgentsarXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue tha→12 Oct 2026Solving VeriContest with a Lean-Backed Rust VerifierarXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a
CompanyOpenAI8 recent entries7 Oct 2026CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance FootagearXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both huma→8 Oct 2026Why VLMs Miss Small Objects, and When Zooming In Is SafearXiv:2610.09313v1 Announce Type: new Abstract: Vision-language models (VLMs) often miss small objects in large images. We ask three questions: what limits them, which of these limits better models ca→8 Oct 2026Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic SciencearXiv:2610.09446v1 Announce Type: new Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not de→9 Oct 2026Writing for the Reviewer: Defensive Writing in GPT ModelsarXiv:2610.11355v1 Announce Type: new Abstract: Researchers increasingly use ChatGPT to revise their papers, and recent GPT versions often narrow or even retract the authors' claims. We call such chan→9 Oct 2026Why LLM Agents Favor Their Group: Stakes, Observed Norms, and ReputationarXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis→9 Oct 2026Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific WritingarXiv:2610.11599v1 Announce Type: cross Abstract: Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this scree→9 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
CompanyGoogle8 recent entries9 Oct 2026DataVista: Diagnosing Multimodal LLMs on Data Video UnderstandingarXiv:2610.11993v1 Announce Type: cross Abstract: Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis. Compared w→9 Oct 2026Conversational Voice Aesthetic Model with Reinforcement Learning from Human ListenersarXiv:2610.10868v1 Announce Type: cross Abstract: We introduce Conversational Voice Aesthetic Model, a speech large language model for describing the voice aesthetics of real or synthetic speech respo→9 Oct 2026Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial GatekeeperarXiv:2610.11542v1 Announce Type: cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden→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→12 Oct 2026People Making Conversation: Evaluating How Naturally Speech Models ConversearXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg→12 Oct 2026MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure GenerationarXiv:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted r→12 Oct 2026APEX-Harm: Evaluating Agent Safety in Shared Professional WorkspacesarXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine→12 Oct 2026AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum LearningarXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re
CompanyMeta8 recent entries12 Oct 2026Hyper Algorithm Design Agent: Evolving Learnable Optimizer from ZeroarXiv:2609.35328v2 Announce Type: replace Abstract: Meta-Black-Box Optimization (MetaBBO) is one of the highlights in the recent AI for Optimization trend. This paradigm's bi-level workflow leverages →12 Oct 2026Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral ComparisonarXiv:2610.13082v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored as facilitators of group discussion and collaborative work, but the behavioral differences →12 Oct 2026DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMsarXiv:2610.13767v1 Announce Type: cross Abstract: Low-bit inference on accelerators with native 4-bit support requires quantizing both weights and activations to realize the full throughput gains thes→12 Oct 2026CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement LearningarXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although →12 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→12 Oct 2026Byzantine-Resilient Federated Large Language Model via Hypergraph Message PassingarXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is→12 Oct 2026Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsarXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d→12 Oct 2026Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with HumansarXiv:2610.13303v1 Announce Type: cross Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-
CompanyMistral8 recent entries6 Oct 2026The Universal Weight Subspace HypothesisarXiv:2512.05117v3 Announce Type: replace-cross Abstract: We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the→7 Oct 2026Monte Carlo Estimation for KV Cache EvictionarXiv:2610.07643v1 Announce Type: cross Abstract: Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask, which memory will matter whil→8 Oct 2026Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical InputsarXiv:2610.09033v1 Announce Type: new Abstract: Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment rout→8 Oct 2026How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by SuppressionarXiv:2610.09624v1 Announce Type: cross Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds d→8 Oct 2026Document-Level Text Simplification in Estonian Using Large Language ModelsarXiv:2610.10378v1 Announce Type: new Abstract: Document-level text simplification involves transformations that go beyond sentence-internal edits, addressing discourse coherence, anaphora resolution,→9 Oct 2026Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RLarXiv:2607.16204v2 Announce Type: replace Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixe→9 Oct 2026LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMsarXiv:2610.11160v1 Announce Type: new Abstract: Lifelong editing of LLMs requires storing thousands of edits after acquisition. A widely used family of approaches attaches one LoRA adapter per edit, w→12 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
CompanyxAI8 recent entries7 Oct 2026CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance FootagearXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both huma→8 Oct 2026Revisiting Explainable AI through Model-Independent Concept DictionariesarXiv:2610.10301v1 Announce Type: new Abstract: Modern applications of AI rely on increasingly complex models. Explainable AI (XAI) has emerged as a set of techniques aimed at improving model transpar→8 Oct 2026For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature ImportancearXiv:2610.09844v1 Announce Type: cross Abstract: The adoption of machine learning for socially relevant tasks requires effective explainable artificial intelligence (XAI) methods to better understand→9 Oct 2026WorldBench: Evaluating LLMs on Three.js Voxel World GenerationarXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak→12 Oct 2026People Making Conversation: Evaluating How Naturally Speech Models ConversearXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg→12 Oct 2026Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature ImportancearXiv:2610.12493v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) tools have often been presented as methods to increase trust in machine learning models by making aspects of t→12 Oct 2026Controlled-Minimax: Stabilizing Adversarial Optimization via Control TheoryarXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles o→12 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
CompanyDeepSeek8 recent entries12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still →12 Oct 2026Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue ResolutionarXiv:2610.13563v1 Announce Type: cross Abstract: Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests, →12 Oct 2026MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data SynthesisarXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether→12 Oct 2026Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAarXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-→12 Oct 2026Let Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question AnsweringarXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me→12 Oct 2026Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border CommunitiesarXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti→12 Oct 2026Can Language Models Play the Wikipedia Game?arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ→12 Oct 2026Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV HierarchyarXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only th
CompanyNVIDIA8 recent entries9 Oct 2026SatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique ImagearXiv:2610.11049v1 Announce Type: new Abstract: We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from→9 Oct 2026Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than RecomputearXiv:2610.10845v1 Announce Type: cross Abstract: A large language model can only use the text that fits in its context window, and it recomputes its internal key-value (KV) state for a prompt every t→9 Oct 2026Read What Matters: Query-Adaptive Quantization for KV CachesarXiv:2610.11245v1 Announce Type: cross Abstract: KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch→9 Oct 2026GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and MappingarXiv:2610.12411v1 Announce Type: new Abstract: Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robot→9 Oct 2026DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert CompositionarXiv:2610.11317v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with recent work demonstrating the benefits of fine-grai→9 Oct 2026Demonstrating Arena 5.0: A Photorealistic ROS2 Simulation Framework for Developing and Benchmarking Social NavigationarXiv:2610.11220v1 Announce Type: new Abstract: Building upon the foundations laid by our previous work, this paper introduces Arena 5.0, the fifth iteration of our framework for robotics social navig→12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still →12 Oct 2026RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language ModelsarXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the add