CompanyAnthropic8 recent entries1 Oct 2026When Scientific Contradictions Are Lost in TranslationarXiv:2609.38621v1 Announce Type: new Abstract: Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparab→1 Oct 2026DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
CompanyOpenAI8 recent entries2 Sept 2026From Tool Use to Technological Agency: LoopCAT as a Local-First, Open-Source Tool for Translation Technology EducationarXiv:2609.00344v1 Announce Type: new Abstract: Translation students need to learn both how to use translation technologies and how to judge the choices those technologies make available. This article→7 Sept 2026Substrate-Aware AI Agents: Execution Context as a First-Class InputarXiv:2609.05232v1 Announce Type: new Abstract: Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine w→15 Sept 2026The Troy Moment of AI: Why SomeWill Cheat and SomeWill Follow?arXiv:2609.15494v1 Announce Type: new Abstract: Recent investigations of the July 2026 OpenAI--Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned ta→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→17 Sept 2026WetRobo: A Reproducible Robot Kit for Coding Agents in Biological LaboratoriesarXiv:2609.18435v1 Announce Type: new Abstract: Automating biological research requires general-purpose, reproducible robot systems that allow individual wet-lab researchers to delegate robot tasks wi→1 Oct 2026Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain AttacksarXiv:2609.38415v1 Announce Type: cross Abstract: This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI syste→1 Oct 2026AIfred: Augmented Learning through Functional Robotic Embodiment at the DeskarXiv:2609.38737v1 Announce Type: new Abstract: Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separat→2 Oct 2026A First Glance at Jev for Network Traffic Classification: Accuracy, Processing Time, and CostarXiv:2610.00376v1 Announce Type: new Abstract: We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet tim
CompanyGoogle8 recent entries17 Sept 2026Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier ModelsarXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre→17 Sept 2026How AI Assistants Respond to Repeated AbusearXiv:2609.17547v1 Announce Type: new Abstract: AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement →23 Sept 2026Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed EngineersarXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned,→24 Sept 2026ChronosAttack: Adversarial Tool Scheduling Attacks on LLM AgentsarXiv:2609.27857v1 Announce Type: cross Abstract: Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introd→25 Sept 2026The Last Human Gate: Forward Deployed Engineering for Governance AutomationarXiv:2609.29345v1 Announce Type: new Abstract: Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human impleme→1 Oct 2026EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific DiscoveryarXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents →1 Oct 20264MT-VLM: How Coarse Is a VLMs Cognitive Map?arXiv:2609.39238v1 Announce Type: new Abstract: An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, eac→9 Oct 2026GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQAarXiv:2610.11402v1 Announce Type: new Abstract: GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making p
CompanyMeta5 recent entries31 Jul 2026Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning EngineeringarXiv:2607.28568v1 Announce Type: new Abstract: Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a →17 Aug 2026AI-Assisted Discovery and Construction of a Counterexample to the Convergence of Three-Block ADMM with the Identity Matrix as its Third Constraint BlockarXiv:2608.14396v1 Announce Type: cross Abstract: The alternating direction method of multipliers (ADMM), as a landmark algorithm, has attracted tremendous research attention and extensive practical a→18 Aug 2026Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice BenchmarksarXiv:2608.15428v1 Announce Type: cross Abstract: Multiple-choice benchmarks are graded on whether a model picks the right option, not on whether it needed the question. Measuring that gap takes care:→26 Aug 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent HarnessesarXiv:2608.24876v1 Announce Type: new Abstract: Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We in→2 Sept 2026From Tool Use to Technological Agency: LoopCAT as a Local-First, Open-Source Tool for Translation Technology EducationarXiv:2609.00344v1 Announce Type: new Abstract: Translation students need to learn both how to use translation technologies and how to judge the choices those technologies make available. This article
CompanyxAI6 recent entries28 Jul 2026Who Gets Named: Citation Type Predicts Individual Naming by Grounded Language Models, and a Roster Instrument Captures 0.5% of ItarXiv:2607.23893v1 Announce Type: cross Abstract: Prior work on AI brand visibility measures the firm: does a model recommend a company, and does that track its reputation. This study asks the questio→5 Aug 2026AI Security Leaderboard: Methodology, Results and Minimal StandardarXiv:2608.03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much pro→13 Aug 2026The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering BenchmarkarXiv:2608.11469v1 Announce Type: cross Abstract: AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequent→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→17 Sept 2026Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier ModelsarXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre→1 Oct 2026DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
CompanyDeepSeek8 recent entries18 Aug 2026StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness ScalingarXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate→27 Aug 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness EvolutionarXiv:2608.25593v1 Announce Type: new Abstract: Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/s→23 Sept 2026Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed EngineersarXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned,→24 Sept 2026ChronosAttack: Adversarial Tool Scheduling Attacks on LLM AgentsarXiv:2609.27857v1 Announce Type: cross Abstract: Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introd→25 Sept 2026The Last Human Gate: Forward Deployed Engineering for Governance AutomationarXiv:2609.29345v1 Announce Type: new Abstract: Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human impleme→5 Oct 2026EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace AgentsarXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources→7 Oct 2026ServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?arXiv:2610.07792v1 Announce Type: cross Abstract: Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correct→9 Oct 2026Evaluating Rubric Generation with Interventional TransferarXiv:2610.10809v1 Announce Type: new Abstract: Instance-specific rubrics are common in AI benchmarks where reliable evaluation requires specific expert knowledge. This approach is difficult to scale,
CompanyNVIDIA1 recent entries5 Oct 2026D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?arXiv:2610.03226v1 Announce Type: cross Abstract: GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal ho