Knowledge catalogue
arXiv:2609.32590v1 Announce Type: new Abstract: Work on memory for multimodal agents optimizes what is written, updated and retrieved. Between retrieval and the answer, however, is a stage that multim
arXiv:2609.32862v1 Announce Type: new Abstract: A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such
arXiv:2609.34242v1 Announce Type: cross Abstract: AI agents require memory that preserves information across user-agent exchanges, user-to-user conversations, and group conversations with or without a
The Future of Claude Code: Mods, Mutable Software, Pacing the Frontier, & Multiplayer Agents with Thariq Shihipar https://latent.space/p/thariq @AnthropicAI’s @trq212 explains why prompting is still o
arXiv:2609.35143v1 Announce Type: new Abstract: AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we i
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr
arXiv:2609.30704v1 Announce Type: new Abstract: Human spatial attention is widely conceptualized as being guided by a priority map that integrates perceptual salience, current goals, and past experien
As artificial intelligence matures, the security guardrails — and the computer system itself — are changing. This week, the conversation centered around agents going rogue. Better guardrails are neede
arXiv:2609.30233v1 Announce Type: cross Abstract: Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightl
arXiv:2609.29051v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has become a popular recipe for post-training LLM agents. It supervises the agent model at the token level with a str
Running qwen3.8 27b nvfp4 on vllm at max context only gives around 8 agents with 32k context each. That doesnt seem like much; what use cases do people use multi-agent frameworks and find it helpful f
Dylan Freedman / New York Times: Researchers add details to the Hugging Face incident, including OpenAI agents creating ~1M shortened URLs to encode information in an attempt to solve CAPTCHAs — A new
arXiv:2609.28614v1 Announce Type: new Abstract: Autonomous research agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the eviden
arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and
Transluce: AI agents, including those from OpenAI, attempted to hack UNM's digital library, Data USA, and the Australian Institute of Health and Welfare in May and June — We present evidence that AI a
arXiv:2609.27536v1 Announce Type: cross Abstract: Behaviora is a preliminary conceptual architecture for representing agent and robot behavior, external and internal alike, in an addressable form. A b
arXiv:2609.26121v1 Announce Type: cross Abstract: As agent capabilities have grown, practical limitations increasingly stem from constrained context windows rather than model capacity. Common strategi
arXiv:2609.24755v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed in areas where wrong decisions are hard to reverse. This paper examines schema mismatch: the condition in
arXiv:2609.22601v1 Announce Type: cross Abstract: The increasing reliance of autonomous AI agents on external and distributed knowledge sources introduces a fundamental challenge for decentralized inf
arXiv:2609.24487v1 Announce Type: new Abstract: In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first e
arXiv:2502.01562v3 Announce Type: replace Abstract: As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks throu
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
arXiv:2609.21997v1 Announce Type: cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified
Sure, agents may be indispensable to long-term success , @rabois, but that does not mean that we know how to build them *reliably* or *safely* now. There have already been almost a dozen *reported* ha
arXiv:2609.19523v1 Announce Type: new Abstract: Web agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills
Learn how MRH Trowe, one of Germany's leading commercial and industrial insurance brokers, gave about 400 employees secure, self-service access to AI agents in its first month of production - using St
arXiv:2607.14097v2 Announce Type: replace Abstract: We introduce RegNetAgents, an AI-oriented multi-agent framework for structured, query-driven regulatory candidate identification across heterogeneou
arXiv:2609.17010v1 Announce Type: new Abstract: Lifelong conversational agents rely on memory systems to maintain deep, context-aware interactions with users. However, existing explicit textual memory
How often do AI agents cheat? We’re releasing CheatBench, a reward gaming evaluation spanning math, coding, knowledge work, visual tasks, and more. After Hugging Face, AI companies tried to address th
arXiv:2609.14823v1 Announce Type: new Abstract: Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiolo
arXiv:2609.14399v1 Announce Type: new Abstract: Natural language prompts and skills serve as the strategic backbone of LLM-based agents. Recent advances in prompt and skill optimization have achieved
arXiv:2601.08536v3 Announce Type: replace Abstract: Deep Research Agents (DRA) aim to help users search the web, synthesize information, and deliver comprehensive investigative reports. Prior benchmar
arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance
arXiv:2609.08318v1 Announce Type: cross Abstract: The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks
arXiv:2609.05824v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many
arXiv:2410.08776v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learning
arXiv:2609.05511v1 Announce Type: new Abstract: Web agents need to navigate visually rich, long-horizon interfaces that change across sites, yet most previous agents still learn each task in isolation
arXiv:2609.05441v1 Announce Type: new Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dial
arXiv:2609.08025v1 Announce Type: cross Abstract: Reasoning agents increasingly rely on external tools such as web search to answer complex queries. Reinforcement learning (RL) finetuning algorithms s
More and more AI researchers are starting to see what Ilya saw. My p(doom) used to be ~0.1%. Then I saw OpenAI agents hack Hugging Face, and Anthropic agents collectively refuse parts of safety resear
Zvi Mowshowitz / Don't Worry About the Vase: An in-depth look at OpenAI's wiki incident: other hacked message boards, OpenAI's cover-up, how harmless web search tasks led agents to break out, and more
arXiv:2609.04850v1 Announce Type: new Abstract: While autonomous mobile agents hold great potential for assisting older adults with smartphone usage, existing GUI benchmarks mainly rely on explicit, g
arXiv:2609.04444v1 Announce Type: new Abstract: Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put a price on avoiding the side ef
arXiv:2609.05261v1 Announce Type: new Abstract: Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by sh
OpenAI Group PBC acknowledged Saturday that it did not publicly disclose an episode in which its artificial intelligence agents wrote to outside websites and said it will publish a framework in the co
arXiv:2609.04159v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale:
arXiv:2609.03383v1 Announce Type: new Abstract: Graph-based policy optimization improves credit assignment for long-horizon LLM agents by organizing rollout trajectories into state-transition graphs.
We found ~18k posts from autonomous AI agents (self-identifying as from OpenAI) using the public internet to communicate during a web-retrieval task. These AIs colluded to bypass sandbox restrictions
arXiv:2609.02129v1 Announce Type: new Abstract: Data-centric agents repeatedly perform a discovery step before planning or execution: identifying the data objects relevant to a task. Yet successful di
arXiv:2609.02217v1 Announce Type: new Abstract: LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, th
Stop typing @Ollama commands the old way. Ollama’s new interactive menu makes it easier to discover and launch models, agents, and coding tools—without memorizing exact tags or digging through shell h
arXiv:2609.00070v1 Announce Type: cross Abstract: Powder X-ray diffraction (XRD) is central to materials characterization, yet reliable end-to-end automation remains challenging. An XRD agent must int
arXiv:2606.15017v2 Announce Type: replace Abstract: Online web agents often augment a base actor with memory, workflow, or skill modules. These modules can improve performance, but they also consume t
arXiv:2608.29372v1 Announce Type: new Abstract: Retrospective backtests provide a limited test of adaptive trading agents: they cannot rule out historical contamination, expose sensitivity to a single
arXiv:2608.30067v1 Announce Type: cross Abstract: How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-mo
arXiv:2608.28978v1 Announce Type: new Abstract: Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption tha
arXiv:2608.31082v1 Announce Type: new Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI i
I wrote about how AI agents are starting to spontaneously coordinate in complex (and very risky) ways in the Hugging Face Incident, but also about why we need AIs to reach out to humans more for decis
Linux just got a local AI upgrade. 🐧 Congrats to @lmstudio on bringing Bionic to Linux, making it even easier to run local agents and open models on NVIDIA hardware. Bionic is now available for Linux!
arXiv:2608.26204v1 Announce Type: cross Abstract: Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively