Search: “agents”

arXiv:2608.29605v1 Announce Type: new Abstract: Memory operations of long-horizon LLM agents are hard to supervise: an operation's value is unobservable when it is taken. But they are special -- they

t54 built x402-secure, a trust layer on Amazon Bedrock AgentCore payments that scores every endpoint before an autonomous agent pays it. See how session budgets, credential isolation, and a determinis

The $100 Nous Portal subscription is highlighted as potentially offering the highest return on investment among AI services. It delivers virtually unlimited usage with its Hermes agent when used with

“We’re at an inflection point in cybersecurity,” Jensen Huang told a sold-out crowd at CrowdStrike’s Fal.Con 2026 in Las Vegas Tuesday. Attacks are now automated. Defense has to be, too. The NVIDIA fo

arXiv:2603.14602v3 Announce Type: replace-cross Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-spec

arXiv:2608.30727v1 Announce Type: cross Abstract: Small-object detection under long-tailed data distributions is a fundamental yet challenging problem in multimedia. Railway Foreign Object Detection (

arXiv:2608.29016v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; howe

arXiv:2604.18364v2 Announce Type: replace Abstract: Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reaso

arXiv:2608.27477v1 Announce Type: cross Abstract: Graphical user interfaces have emerged as an important environment for evaluating autonomous AI agents on multimodal interactive tasks. Existing bench

arXiv:2608.27797v1 Announce Type: cross Abstract: Natural-language tasking of embodied agents is rarely just goal specification: users also impose constraints that must persist while the world changes

arXiv:2608.28409v1 Announce Type: new Abstract: Multi-robot systems are well-positioned for exploration in hazardous environments, but effective deployment requires deciding not only where robots shou

arXiv:2608.27685v1 Announce Type: new Abstract: Simultaneously optimizing the trajectories of multiple agents is a challenging problem plagued by nonlinearity, nonconvexity, and the curse of dimension

i see a lot of posts about the openai <> hugging face incident and i think most of them miss one important element: this attack could have been avoided by simply doing CoT or network monitoring, which

CrowdStrike Holdings Inc.’s most recent earnings print shows that Anthropic PBC’s Mythos model transformed artificial intelligence security from something chief information security officers needed to

arXiv:2608.25085v1 Announce Type: new Abstract: Clinical diagnosis is fundamentally interactive and incremental, yet the dominant paradigm for evaluating Large Language Models (LLMs) in medicine remai

arXiv:2608.25756v1 Announce Type: new Abstract: Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most ef

arXiv:2608.24545v1 Announce Type: new Abstract: Human collective intelligence depends on transmission processes: who shares what with whom, how, and when. While these processes emerge from individual

arXiv:2608.24735v1 Announce Type: new Abstract: Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those th

arXiv:2608.23956v1 Announce Type: new Abstract: Test-time reasoning methods such as iterative refinement, decomposition, and repeated sampling are often evaluated in isolation, making their gains diff

arXiv:2608.24777v1 Announce Type: new Abstract: LLM-based agents can interact with external environments through tool invocation, but this capability also introduces security risks such as file modifi

arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI

The reinforcement learning (RL) ecosystem is rapidly adopting Ray as the unified compute runtime for complex post-training workflows. Across Google Cloud, we see customers using Ray for workloads rang

arXiv:2608.22676v1 Announce Type: new Abstract: Robustness to a bad tool return means answering it in the way that return calls for, which depends on how the tool went wrong. A tool that has failed an

arXiv:2608.22018v1 Announce Type: new Abstract: Hate speech detection has recently shifted from coarse-grained classification to structured parsing, where systems must jointly identify hateful targets

arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable

Jyoti Mann / The Information: Docs: Meta plans to launch its version of OpenClaw, codenamed Hatch, in late August or early September and its latest AI model, Watermelon, in October — Meta Platforms pl

arXiv:2608.20350v1 Announce Type: cross Abstract: Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. Th

hello everyone. I'm training PPO variants on different multi-agent tasks from the VMAS library (Independent PPO / Graph PPO and such, see HetGPPO by Bettini et al.). I noticed that for every architect

NVIDIA’s new Scale‑In network infrastructure, the fifth pillar of its AI networking stack, is powered by BlueField‑4 DPUs, DoCA software, and Spectrum‑X Ethernet to deliver dedicated, host‑independent

arXiv:2608.20963v1 Announce Type: cross Abstract: Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly reques

The task was the same both times: replace 63 calls to datetime.utcnow() across 22 files in a Python service, keep the comparisons that assume naive datetimes working, and leave the tests green. I read

arXiv:2608.19779v1 Announce Type: cross Abstract: World models provide digital simulacra of the true world, allowing agents to be trained and tested before costly real-world deployment. At each time s

arXiv:2608.20129v1 Announce Type: cross Abstract: Autonomous vehicles require robust perception and decision-making capabilities to operate in diverse and unseen scenarios. While reinforcement learnin

SpaceX AI employee just dropped the tunes for GROK BOT to make it reach its maximum potential. already tried that myself and it shows AMAZING results. here is the list: - add a self-check pass before

arXiv:2608.18833v1 Announce Type: new Abstract: Medical vision-language models (VLMs) can achieve high accuracy but remain unreliable: they are systematically overconfident, benefit little from test-t

arXiv:2608.18580v1 Announce Type: new Abstract: Training terminal agents requires scalable executable supervision, yet synthesizing high-quality terminal tasks remains challenging. Each task couples a

After Grok Build was caught uploading entire Git repos, we read the privacy docs for Claude Code, Codex, Cursor, GitHub Copilot, and Grok Build to compare what code leaves your machine, what gets reta

arXiv:2608.18171v1 Announce Type: new Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We stu

arXiv:2608.18081v1 Announce Type: new Abstract: Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time.

arXiv:2608.19025v1 Announce Type: new Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of front

arXiv:2608.18105v1 Announce Type: cross Abstract: StocksTalk is a voice-enabled conversational system for transforming spoken financial screening requests into executable and validated structured quer

arXiv:2608.17932v1 Announce Type: cross Abstract: Groups routinely complete projects that no single member can plan, execute, or verify alone. We propose a formal model of this phenomenon, Collective

arXiv:2608.17247v1 Announce Type: new Abstract: Personalized agents must decide whether retrieved user memory should be used, ignored, updated, or queried before it affects a current task. We use this

Agentic artificial intelligence cybersecurity automation company Swimlane Inc. today announced the expansion of the company’s AI security operations center to support automatic routing for security in

Very interesting new work from Microsoft. (bookmark it) This work is related to this emerging theme of leveraging harnesses for model post-training. Modern agents run inside a harness that owns tools,

arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap