CompanyAnthropic8 recent entries1 Oct 2026The Backdrop Exposes What the World Around an Agent Costs ItarXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send →1 Oct 2026OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable RuntimearXiv:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically as
CompanyOpenAI8 recent entries1 Sept 2026The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research AgendasarXiv:2603.11842v2 Announce Type: replace-cross Abstract: The post-ChatGPT surge has rapidly reframed IS research and practice. As organizations and society grapple with GenAI adoption, a body of seco→3 Sept 2026Addressing Trust in AI Systems through Education: A Didactic PerspectivearXiv:2609.02453v1 Announce Type: cross Abstract: Machine learning (ML) education faces two persistent and connected obstacles: many educational tools present ML as an opaque black box, which leaves l→9 Sept 2026Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM AgentsarXiv:2609.05911v1 Announce Type: cross Abstract: Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize →15 Sept 2026Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type→18 Sept 2026Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding AgentsarXiv:2609.19587v1 Announce Type: cross Abstract: To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before i→21 Sept 2026Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI DialoguearXiv:2609.21401v1 Announce Type: cross Abstract: Conversational AI systems produce fluent, socially appropriate responses, yet whether they participate in cooperative communication or merely simulate→30 Sept 2026The Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AIarXiv:2609.36069v1 Announce Type: cross Abstract: Generative AI (Gen AI) is reshaping how individuals learn and work, but its consequences for collective knowledge, the shared body of knowledge that o→7 Oct 2026MiniScope: Authorizing Agents with Least-Privilege PermissionsarXiv:2512.11147v2 Announce Type: replace-cross Abstract: AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a
CompanyGoogle8 recent entries25 Sept 2026Robo-Harness K1: Harnessing Robot-Use Agents via Perception AugmentationarXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulat→25 Sept 2026OCC4M: Object-Centric 4D Memory for Spatiotemporal Reasoning in Long-Horizon ManipulationarXiv:2609.28798v1 Announce Type: new Abstract: Long-horizon manipulation often requires reasoning about state absent from the current view, such as a vanished object's location, temporal identity, or→28 Sept 2026HaM-World: Soft-Hamiltonian World Models with Selective Memory for PlanningarXiv:2605.05951v2 Announce Type: replace Abstract: World models support model-based planning through learned latent dynamics, but imagined rollouts can become unstable as the planning horizon grows o→29 Sept 2026See, Measure, and Reason: Learning Visually Grounded Reasoning in PathologyarXiv:2609.34277v1 Announce Type: new Abstract: Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pat→30 Sept 2026Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D ScenesarXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont→1 Oct 2026Cogentic: Multi-Agent Orchestration for Automated Proof DiscoveryarXiv:2609.40324v1 Announce Type: new Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong m→7 Oct 2026Who Wrote It Is Not Enough: Detecting Who Contributed the InsightarXiv:2610.07365v1 Announce Type: new Abstract: As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contribut→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 entries5 Oct 2026Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research AgentsarXiv:2610.02525v1 Announce Type: new Abstract: Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because suc→5 Oct 2026iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVDarXiv:2610.02815v1 Announce Type: new Abstract: Long chain-of-thought reasoning substantially increases KV-cache memory during autoregressive decoding, as every generated token introduces new key and →7 Oct 2026Fork-and-Flush: Escaping Idea Basins in Autoresearch AgentsarXiv:2610.07447v1 Announce Type: new Abstract: Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent expe→7 Oct 2026Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced SycophancyarXiv:2610.07403v1 Announce Type: new Abstract: Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-→8 Oct 2026Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice EvaluationarXiv:2610.10368v1 Announce Type: cross Abstract: Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known a→9 Oct 2026Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State QuantizationarXiv:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent →9 Oct 2026Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug FixesarXiv:2610.11963v1 Announce Type: cross Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adj→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
CompanyMistral8 recent entries29 Jul 2026Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip AttacksarXiv:2607.25227v1 Announce Type: cross Abstract: Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly →11 Aug 2026Spectral Outliers Reveal Dominant Learned Structure in Transformer AttentionarXiv:2608.07921v1 Announce Type: cross Abstract: We apply Marchenko-Pastur (MP) random matrix theory to pre-trained attention weights in order to separate each projection matrix into a random-like bu→2 Sept 2026CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMsarXiv:2609.01161v1 Announce Type: new Abstract: Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce Cop→21 Sept 2026Understanding LLM Quantization through Activation-Guided Compensation and Orthogonal ResidualsarXiv:2609.21450v1 Announce Type: new Abstract: Post-training weight-activation quantization reduces the memory and inference costs of large language models, but aggressive W4A4 quantization remains d→22 Sept 2026Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol StatesarXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i→23 Sept 2026Block-Level Weight-Space Structure Persists Under Post-Training: An Empirical Study Across LLM FamiliesarXiv:2609.26147v1 Announce Type: new Abstract: Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present →24 Sept 2026Alignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override ResistancearXiv:2609.27333v1 Announce Type: new Abstract: Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions→25 Sept 2026Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM AgentsarXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later mod
CompanyxAI8 recent entries31 Jul 2026AI LEGO: Scaffolding Cross-Functional Collaboration in Industrial Responsible AI Practices during Early Design StagesarXiv:2505.10300v2 Announce Type: replace-cross Abstract: Responsible AI (RAI) efforts increasingly emphasize the importance of addressing potential harms early in the AI development lifecycle through→4 Aug 2026Empirical investigation of 3D CT Foundation Models and Unsupervised Adaptation for Head and Neck Cancer Recurrence PredictionarXiv:2608.00071v1 Announce Type: new Abstract: The rapid emergence of 3D CT foundation models has opened new avenues for predictive modeling from CT imaging, offering a compelling alternative to trad→10 Aug 2026Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained TransformersarXiv:2608.07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head. Muon groks modular addition faster, but its solutions do not hold.→13 Aug 2026A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBencharXiv:2608.12138v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but s→9 Sept 2026VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference IdentificationarXiv:2609.06245v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often strugg→15 Sept 2026Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type→16 Sept 2026Self-reported archetypes and behavioral failures in Large Language ModelsarXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o→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
CompanyDeepSeek8 recent entries30 Sept 2026SAGE: A Statistical Acceptance Gate for Self-Evolving AgentsarXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and→1 Oct 2026WorkGenesis: Building the Worlds That Teach Agents to WorkarXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents require→1 Oct 2026Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot ToolsarXiv:2609.39018v1 Announce Type: cross Abstract: Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code→1 Oct 2026Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent SystemsarXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has ex→5 Oct 2026iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVDarXiv:2610.02815v1 Announce Type: new Abstract: Long chain-of-thought reasoning substantially increases KV-cache memory during autoregressive decoding, as every generated token introduces new key and →6 Oct 2026When Is Enough Enough in Self-Evolving LLM Systems?arXiv:2610.04756v1 Announce Type: cross Abstract: Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifac→7 Oct 2026Who Wrote It Is Not Enough: Detecting Who Contributed the InsightarXiv:2610.07365v1 Announce Type: new Abstract: As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contribut→9 Oct 2026FlowState: Execution State as Memory for Long-Horizon LLM AgentsarXiv:2609.34565v2 Announce Type: replace Abstract: Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases co
CompanyNVIDIA8 recent entries17 Sept 2026Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated DrivingarXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We in→18 Sept 2026Astronex-World 1.0: Real-Time Interactive World Model FoundationarXiv:2609.20034v1 Announce Type: cross Abstract: We present Astronex-World 1.0, an open controllable video world-model foundation. Given a text prompt (text-to-video) or an initial observation (image→22 Sept 2026Scout: Open-World Species Recognition on the EdgearXiv:2609.22897v1 Announce Type: new Abstract: Large vision-language models (VLMs) enable recognition beyond a fixed class set, but their computational demands prevent them from running on many edge →23 Sept 2026RoofLang: Enabling AI-Driven Architecting of LLM Inference SystemsarXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based. →24 Sept 2026DUGM-R: Uncertainty-Aware Dynamic Grid Mapping and Risk-Triggered Recovery for Learned Local NavigationarXiv:2609.27338v1 Announce Type: new Abstract: Learned local navigation in crowded indoor environments is sensitive to how dynamic obstacle motion is represented, while collision-prone behaviour may →28 Sept 2026TRACKGRAPH: Online Open-Vocabulary 3D Scene Graphs via Image-Space TrackingarXiv:2609.31005v1 Announce Type: new Abstract: Open-vocabulary 3D maps enable robots to reason about previously unknown environments using natural language. However, existing systems typically segmen→29 Sept 2026AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied AgentsarXiv:2609.33299v1 Announce Type: new Abstract: World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequence→7 Oct 2026SoloQ: Calibration-Free Quantization for Diffusion Language ModelsarXiv:2610.07121v1 Announce Type: new Abstract: Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based t