Knowledge catalogue
arXiv:2606.06054v1 Announce Type: new Abstract: Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are l
arXiv:2603.00829v2 Announce Type: replace-cross Abstract: Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is det
arXiv:2603.12109v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons.
arXiv:2606.00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire mor
arXiv:2606.01185v1 Announce Type: new Abstract: Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environm
arXiv:2602.08964v2 Announce Type: replace-cross Abstract: Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals
arXiv:2605.29116v1 Announce Type: new Abstract: When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating
arXiv:2605.29471v1 Announce Type: new Abstract: Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet
This post combines learnings from LangChain’s work on evaluating deep agents and Anthropic’s guide to demystifying evals for AI agents into a practical guide. In this post, you will learn how to: 1) a
arXiv:2605.28775v1 Announce Type: cross Abstract: Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive.
arXiv:2605.28629v1 Announce Type: new Abstract: Recent advancements in multimodal large language models (MLLMs) have shown exceptional potential in enabling mobile-using agents to autonomously execute
arXiv:2605.27955v1 Announce Type: cross Abstract: Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation synt
A highlight of new deepagents release is delta channels Drastically improves how we store checkpoints for agents Deep Agents v0.6 brings Delta channels, reducing checkpoint storage by up to 100x for l
Computer use in Fleet is now in public beta! You can now give your agents in Fleet access to secure virtual machines allowing them to own engineering tasks for you. Use these via Fleet agents in the U
arXiv:2605.27366v1 Announce Type: new Abstract: Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated a
arXiv:2602.17003v2 Announce Type: replace-cross Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail
// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att
arXiv:2605.20023v1 Announce Type: new Abstract: Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by
WisdomAI Inc., creator of an artificial intelligence-native business intelligence platform, is jumping on the agentic AI bandwagon with the latest update to its flagship Federated Agentic Intelligence
arXiv:2603.23638v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly tested on complex tasks, but their ability to allocate scarce resources over long horizons remain
arXiv:2602.16346v3 Announce Type: replace Abstract: LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to ca
arXiv:2605.15706v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existi
Every time I ask my 10-year-old to use coding agents, he gets extremely disappointed. It turns out that all he wants is to build his own rocket simulator. No amount of context engineering helps. No mo
arXiv:2605.16143v1 Announce Type: new Abstract: Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acqui
when evaluating long running agents, all of your evals don't need to be end to end. i'm working on a proper blog about this, but in our evals for our agents that run for 30-60 minutes, we have two set
arXiv:2605.14786v1 Announce Type: cross Abstract: As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model po
arXiv:2605.14290v1 Announce Type: cross Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default
arXiv:2605.08310v1 Announce Type: cross Abstract: Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this
arXiv:2605.07301v1 Announce Type: new Abstract: Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and g
arXiv:2602.12852v2 Announce Type: replace Abstract: Deep Research systems based on web agents have shown strong potential in solving complex information-seeking tasks, yet their search efficiency rema
arXiv:2605.05185v1 Announce Type: new Abstract: Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence v
arXiv:2605.01143v1 Announce Type: new Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, the
arXiv:2605.02592v1 Announce Type: new Abstract: Foundation models, particularly large language models, are increasingly integrated into agent architectures for industrial tasks such as decision suppor
Run an entire company with agents 🔥 It's always awesome to see companies continuing to innovate on AI-native UI/UX, particularly around multi-agent coordination, to solve deeply complex tasks beyond w
NEW paper from Microsoft Research. If you care about training computer-use agents, this is one to keep. (bookmark it) The team builds 1,000 synthetic computers (each with realistic directory structure
arXiv:2604.26522v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents exhibit systemic failures in compositional generalization, limiting their robustness in interactive environments
DeepAgents Deploy is great, you get - a fully open agent harness (no hidden stuff, inspect everything) - managed infra - can use any cocktail of models including Open Models - and everything is traced
arXiv:2601.22154v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However
This is so good @hwchase17 walks through the complete setup of a Deep Agents deployment step-by-step It’s a great example of getting started fast with Deep Agents from the CLI! DeepAgents Deploy is th
arXiv:2604.23815v1 Announce Type: new Abstract: Scientific Deep Research (DR) agents answer user queries by synthesizing research papers into multi-section reports. User feedback can improve their uti
arXiv:2604.24686v1 Announce Type: new Abstract: Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any
last week we dropped a super comprehensive guide on runtime requirements for long running agents! this week i'll be diving into each requirement and runtime capability that meets it, here's the lineup
arXiv:2601.00911v3 Announce Type: replace-cross Abstract: Automated negotiations in insurance and business-to-business (B2B) commerce encounter substantial challenges. Current systems force a trade-of
As AI models improve, technical practitioners are increasingly turning to agentic AI tools to build with Google Cloud products, from Firebase and the Gemini API, to BigQuery and GKE. But how can you e
Workspace agents are AI systems designed to automate tasks and workflows within collaborative work environments, likely covering how these agents can handle scheduling, communication, document managem
arXiv:2601.22149v2 Announce Type: replace Abstract: The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step tow
arXiv:2604.17870v1 Announce Type: new Abstract: Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve p
Real-time decisioning for AI agents requires a foundational customer context layer that provides unified, up-to-date customer data to enable accurate and personalized decisions. Databricks explains ho
arXiv:2604.15719v1 Announce Type: new Abstract: Many consequential decisions must be made before the relevant outcome is known. Such problems are commonly framed as future prediction, where an LLM age
You can use ToolSimulator, an LLM-powered tool simulation framework within Strands Evals, to thoroughly and safely test AI agents that rely on external tools, at scale. Instead of risking live API cal
An open-source debugging tool designed for AI pipelines that provides trace timeline visualization, differential analysis, node replay capabilities, and operates without telemetry, licensed under MIT.
arXiv:2604.13488v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. Whil
arXiv:2510.23853v3 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlook
Ecom-RLVE is a framework for training e-commerce conversational agents using reinforcement learning with verifiable environments that can adapt to different scenarios. The system enables agents to lea
arXiv:2604.05407v2 Announce Type: replace Abstract: LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formattin
Project Think is Cloudflare's initiative to develop next-generation AI agents built on its global network infrastructure, leveraging tools like Workers AI, Durable Objects, and the Workers platform to
arXiv:2510.10073v2 Announce Type: replace-cross Abstract: Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed
arXiv:2604.10343v1 Announce Type: new Abstract: We study the operation of community water systems, where pumps and valves must be scheduled to reliably meet water demands while minimizing energy consu
Great podcast episode that covers OpenAI's Symphony, which dispatches autonomous agents (codex workers) with their own worktrees and tasks. I've found it works well with a layer above Symphony, where
arXiv:2604.09443v1 Announce Type: cross Abstract: Large language model agents receive instructions from many sources-system messages, user prompts, tool outputs, and more-each carrying different level