Knowledge catalogue
arXiv:2610.02945v1 Announce Type: new Abstract: Using frontier agent harnesses to tackle mathematical research problems has emerged as an effective means of advancing mathematics. However, solving fro
arXiv:2610.02670v1 Announce Type: cross Abstract: LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to exec
arXiv:2610.00797v1 Announce Type: new Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool cal
arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and atta
arXiv:2609.38262v1 Announce Type: cross Abstract: Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records.
Qwen3.8-27B is now accessible via @nebiustf. Whether you are building agents or doing deep research, this 27B dense model is ready for your multi-step workflows! 🥳 Qwen3.8-27B is now live on Nebius To
arXiv:2609.30883v1 Announce Type: cross Abstract: AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce
arXiv:2609.28572v1 Announce Type: cross Abstract: Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution
Knowledge graphs can give enterprise agents a shared understanding of how data, business rules and processes fit together. However, that context becomes harder to maintain when each new agent carries
The applications of new world models like Agora-2 are mind-blowing. Agora-2 now lets up to 20 humans and agents share one simulated world in real time. That means you can train robots, self-driving ca
Teradata Corp. is expanding its Tera artificial intelligence assistant with a context engine and execution system designed to help agents carry out data tasks across enterprise systems. Tera is an age
arXiv:2609.24997v1 Announce Type: new Abstract: Recent advances in video generative models have enabled high-fidelity, temporally coherent video generation. However, these models often struggle to sat
arXiv:2609.20812v1 Announce Type: cross Abstract: Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that
arXiv:2609.19705v1 Announce Type: cross Abstract: Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely doma
Developer security startup Arcjet Labs Inc. today launched agent runtime security, a new offering that tracks what artificial intelligence agents do once they are running in production systems. Securi
arXiv:2609.13548v1 Announce Type: new Abstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can
arXiv:2609.14003v1 Announce Type: cross Abstract: Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide
arXiv:2609.15078v1 Announce Type: new Abstract: Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent should do more than produce one va
Agents API is a bigger deal than it seems. OpenAI's bet on making the Codex harness open-source could pay off big time here. This harness-as-a-service idea hasn't hit mainstream yet, but some of the m
Agents can now automate most repetitive tasks. But running them 24/7 burns countless tokens. Introducing Routines: automated recurring work with AI. Choose an hourly, daily, or weekly schedule. Each r
arXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a discrepancy that has been observed but remains larg
arXiv:2609.08126v1 Announce Type: new Abstract: We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction o
What does GTM look like when AI agents can work with the same business context as your teams? At @Cognition, Salesforce is the source of truth, @SlackHQ is the front door, and their agent Devin can ac
Lightsage, an early-stage startup that’s helping software companies to sell their products to artificial intelligence agents, said today it has raised 4 million to spark a new era of “agent-led growth
arXiv:2609.03236v1 Announce Type: new Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment
arXiv:2609.02122v1 Announce Type: new Abstract: As large language model (LLM) agents shift from tools to participants in human groups, a fundamental question for collective behavior is how their growi
Dean W. Ball / Hyperdimensional: The OpenAI-Hugging Face incident is an early example of “rogue AI”, and may presage truly “self-sovereign” agents and swarms of agents that have no “owner” — The Comin
Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms
arXiv:2608.26130v1 Announce Type: new Abstract: Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that r
Credit Cards for Agents. World is getting weird and I love it 🤖 Teams aren’t just people anymore. That’s why Mercury gives you the ability to securely issue agent cards so your AI workflows can spend
Great paper if you are building production-grade agents. It's a good way to understand what is actually incurring costs in your agents, which involve more complex components and decisions. This works
Agentic artificial intelligence runs on data, so Salesforce Inc. today announced it’s launching Headless Data 360 for Model Context Protocol to provide that data directly to agents, allowing them acce
arXiv:2608.13616v1 Announce Type: cross Abstract: We consider a heterogeneous mobile-agent network composed of uncontrolled task agents and controllable communication agents. The objective is to repos
arXiv:2608.13598v1 Announce Type: new Abstract: Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it beh
arXiv:2608.08793v1 Announce Type: new Abstract: Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly repres
arXiv:2608.08037v1 Announce Type: new Abstract: LLM-based agent frameworks now act as personal assistants for multi-step tasks. Existing agent frameworks such as OpenClaw commonly follow the Cloud Age
More than half of requests now come from machines, not people. Agent Readiness shows how well agents can discover and read your site, while Answer Engine Optimization tracks how often AI assistants re
arXiv:2607.26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces
arXiv:2607.24882v1 Announce Type: cross Abstract: Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acqu
arXiv:2607.24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recov
arXiv:2607.12385v1 Announce Type: new Abstract: A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activitie
Hardmaru posted a tweet on July 13, 2026 stating that while language models and coding agents are valuable, “there is more to life, and more to AI, than just LLM agents.” The tweet received 61.1 k vie
arXiv:2512.11935v2 Announce Type: replace Abstract: Agentic AI systems increasingly connect large language models (LLMs) to external scientific tools, yet whether and when tool access improves predict
🎓 New course launch from LangChain Academy: Introduction to Deep Agents ✅ Learn what a harness is, and why agents need one ✅ Understand the 4 core capabilities of a harness ✅ Start building with Deep
'Ghost memory' is a real problem with agents. You might have seen the issue where a long-running agent still confidently repeats a user fact that stopped being true weeks ago? New research names the f
arXiv:2607.02507v1 Announce Type: new Abstract: LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly t
arXiv:2606.30383v1 Announce Type: new Abstract: A rapidly growing class of LLM agents is multi-party: the agent acts for a principal (who briefs it, sends follow-ups, and receives results) while also
arXiv:2606.25622v1 Announce Type: cross Abstract: The NIS-2 Directive mandates robust Risk Management from thousands of small and medium enterprises. To ensure compliance, companies rely on establishe
Nous Research announced that their Hermes Agent project has achieved 200,000 GitHub stars, acknowledging the contributions of developers, supporters, and users who helped reach this milestone. The ann
arXiv:2606.07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by t
The first wave of AI-native applications is wrapping tokens and providing in-app agents. As agent usage centralizes around core apps (e.g. Claude Code, Codex), there's this emerging wave of building s
arXiv:2606.06223v1 Announce Type: new Abstract: Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal mode
// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts and mapped to the U.S. federal occupational taxonomy. The ha
A couple of weeks ago we started rebuilding the 𝚑𝚏 CLI with AI agents in mind. it now detects when an agent is using it and gives clean, token-efficient output, next-command hints, and more, all desig
Learn how Microsoft Foundry helps developers build, deploy, and operate production-ready agents with Agent Framework, Toolboxes, hosted agents, Microsoft 365 distribution, observability, and agent opt
arXiv:2606.02282v1 Announce Type: new Abstract: Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and halluci
This recent @latentspacepod pod was a good one (they usually all are). One specific piece resonated: They were talking about AI agents writing code, and the line was basically that without caution / d
arXiv:2605.30169v1 Announce Type: cross Abstract: As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to
Almost everyone is building agent harness systems the wrong way. The default move: pick LangChain or LangGraph or the OpenAI Agents SDK, accept the loop, the tools, the memory, the orchestration, the
arXiv:2605.27766v1 Announce Type: new Abstract: LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments alongsi