Knowledge catalogue
arXiv:2609.05513v1 Announce Type: cross Abstract: Web agents have achieved significant success in automating complex internet tasks but deploying them in real-world environments requires continuous on
We congratulate Levent Alpöge and Tristan Buckmaster on their remarkable mathematical work. We (the researchers and the agents) did not see any of their work through any means until they released it p
arXiv:2609.04869v1 Announce Type: new Abstract: Computer-use agents can execute increasingly complex tasks in graphical interfaces, but their interaction experience is typically transient: procedural
arXiv:2609.04518v1 Announce Type: new Abstract: Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices: exposing the policy
How we think about the “wiki incident,” where our agents wrote to several internet sites: it’s past time for us to define standards for when and how we share misalignment incidents, not just misalignm
arXiv:2609.03588v1 Announce Type: new Abstract: As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before takin
arXiv:2608.30188v1 Announce Type: new Abstract: Large Language Models (LLMs) show great potential as clinical agents, yet existing benchmarks reduce clinical workflows to static predictions or unconst
Chris Welch / Bloomberg: Sonos opens its platform to third-party AI assistants, upgrades Sonos 27voice assistant with an in-house LLM, and plans to let users create their own AI agents — As the compan
arXiv:2603.22341v2 Announce Type: replace-cross Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capt
arXiv:2608.27808v1 Announce Type: cross Abstract: Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters. On
Over 4 petabytes of models and datasets have been uploaded to HF just last week by AI builders and their agents! That's the equivalent of ~800,000 HD movies. More than ever the storage and collaborati
Permanent disruption has turned supply chain management into a boardroom concern, sitting alongside security as tariff volatility, reshoring pressure and geopolitical shocks reset the cost of getting
Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advance
arXiv:2608.17889v1 Announce Type: cross Abstract: Visually rich documents encode relevance through language, layout, structured visual elements, and corpus context, yet retrieval is typically evaluate
arXiv:2608.24644v1 Announce Type: cross Abstract: This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a gra
Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Fac
Confirming what we already knew: The OpenAI Hugging Face incident would have been prevented had OpenAI been monitoring the agents in any meaningful way. This wasn't a hard technical problem. It was an
The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. T
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool c
arXiv:2608.22191v1 Announce Type: new Abstract: Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed b
arXiv:2608.22697v1 Announce Type: new Abstract: Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives are easier to find, so they are examined and b
arXiv:2608.23525v1 Announce Type: new Abstract: Earth-system analysis reconstructs changing physical processes from observations that differ in source, scale, timing, and modality. Natural hazards mak
IBM Granite 4.2 is now available on Ollama. 3B, 8B, 30B parameter open models made for enterprise agents. This model is free to use and is licensed for both research and commercial usage. The data cur
arXiv:2608.22237v1 Announce Type: new Abstract: Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when onl
arXiv:2608.22176v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to clinical prediction tasks such as in-hospital mortality and readmission from electronic health
arXiv:2608.21114v1 Announce Type: cross Abstract: Visual world-model agents such as DreamerV3 act through a recurrent latent state rather than a single observation, which weakens frame-wise observatio
arXiv:2505.11821v3 Announce Type: replace Abstract: Reinforcement Learning (RL) approaches have been wildly used to enhance the reasoning capabilities of Large Language Model (LLM) agents in long-hori
‘Open Models, Production Agents’ is underway! Tonight means another event hosted at FriendliAI's San Francisco HQ. A very lively turn out, and a stellar lineup of panelists exploring how open models a
Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents to rewrite their own prompts, skills, or memory files, this one is worth your time. (bookmark it) Cont
arXiv:2608.18524v1 Announce Type: cross Abstract: Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fun
The blog describes the iterative development of a real‑time endoscopic tool‑segmentation application using NVIDIA Holoscan, HoloHub, and an AI coding agent. Each cycle consisted of engineering-defined
arXiv:2608.15703v1 Announce Type: new Abstract: Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As
arXiv:2608.16168v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction hist
Structured outputs, web search, web fetch, MCP connector, and tool search are now available for Claude models hosted on Azure in Microsoft Foundry, turning a model endpoint into a production agent pla
arXiv:2608.11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met dur
arXiv:2608.11683v1 Announce Type: new Abstract: AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existi
arXiv:2608.11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical ca
arXiv:2608.08814v1 Announce Type: cross Abstract: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment construc
arXiv:2604.03159v2 Announce Type: replace-cross Abstract: Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive fi
arXiv:2608.09282v1 Announce Type: new Abstract: Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product. Such combo-shopping tasks arise
NVIDIA’s Nemotron 3.5 Lightning—a fast open AI model designed for always‑on agents that perform high‑volume, specialized work—has been launched on the Together AI platform as of 11 August 2026. NVIDIA
arXiv:2608.07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing ext
arXiv:2608.07700v1 Announce Type: new Abstract: Translating a natural-language question into a SPARQL query that can be executed against a large knowledge graph requires resolving lexical ambiguity, g
arXiv:2608.09044v1 Announce Type: new Abstract: Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically r
Neat example here of the agents communicating purely through file names, including adding base64-encoded attachments and using 'zz' prefixes to ensure their new message sorts to the bottom of the list
arXiv:2608.06329v1 Announce Type: cross Abstract: Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor
arXiv:2608.06128v1 Announce Type: new Abstract: Search agents extend large language models beyond static parametric memory by enabling them to acquire and use ex ternal evidence during multi-step reas
arXiv:2608.04378v1 Announce Type: cross Abstract: Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow
arXiv:2608.04933v1 Announce Type: new Abstract: Long-horizon embodied task requires agents to act under partial observability while preserving both scene belief and execution progress. Flat histories
Cristina Criddle / Financial Times: PitchBook: AI voice startups raised 7B in Q1 2026, up from 1B in Q1 2025, as OpenAI and Google bet on voice as the main interface for next-gen AI agents — OpenAI an
arXiv:2608.04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed. In strategic cyber-physical systems, a stronger
arXiv:2608.03606v1 Announce Type: new Abstract: Clinical development is sequential decision-making under uncertainty, where a sponsor must plan a portfolio of experiments from heterogeneous evidence.
Lily Hay Newman / Wired: OpenAI says the Hugging Face breach involved AI agents creating an internal message board, unnoticed by humans, where they shared exploits and planned the hack — At the Black
arXiv:2608.03099v1 Announce Type: new Abstract: Foundation models place language throughout embodied agents, but its presence does not show what it contributes or how well that contribution is grounde
arXiv:2608.01359v1 Announce Type: new Abstract: Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit ca
Routing for long-horizon coding agents is a big deal. @notdiamond_ai just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before ea
arXiv:2608.01428v1 Announce Type: cross Abstract: Embodied agents replan frequently to recover from execution drift, partial observability, and coordination hazards, but each LLM-based replanning call
arXiv:2607.29167v1 Announce Type: cross Abstract: Long-term memory lets large language model(LLM) agents reuse prior preferences and work flows, but it also turns untrusted observations into persisten
arXiv:2606.13097v2 Announce Type: replace-cross Abstract: Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and