Knowledge catalogue
arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents
arXiv:2509.02910v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act on people's behalf: they write emails, buy groceries, and book restaurants. While the outsourcin
arXiv:2608.18389v1 Announce Type: new Abstract: AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly underst
arXiv:2608.18050v1 Announce Type: new Abstract: AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets,
notes on 'How to do data' from th Zai team that others should steal as they build their own environments - 'Research agents collect task patterns from real work and turn them into runnable long-horizo
arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Exist
arXiv:2608.10424v1 Announce Type: new Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have in
arXiv:2608.10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over t
arXiv:2602.07796v2 Announce Type: replace Abstract: User-engaged LLM agents increasingly operate in service scenarios where task success depends on coordination between the agent, the user, and a stat
arXiv:2608.08601v1 Announce Type: new Abstract: To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them. However, existing AI risk taxonomies focus on broad
arXiv:2607.28956v1 Announce Type: new Abstract: Large language model agents are increasingly evaluated as autonomous tool users, yet most benchmarks focus on bounded tasks with immediate success crite
arXiv:2607.27191v1 Announce Type: cross Abstract: Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is t
arXiv:2607.26375v1 Announce Type: new Abstract: Coding agents (e.g., Cursor) improve developer productivity by optimizing task completion, but shifting users from writing code to prompting and reviewi
arXiv:2607.26922v1 Announce Type: new Abstract: Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial m
arXiv:2607.25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and a
arXiv:2607.15263v3 Announce Type: replace-cross Abstract: Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, e
arXiv:2607.22569v1 Announce Type: new Abstract: Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, an
arXiv:2607.10856v2 Announce Type: replace-cross Abstract: The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with
Snowflake Inc. today introduced Cortex AI Gateway, a centralized control layer that lets enterprises connect, govern and monitor artificial intelligence agents as they reach into models, tools, Model
here’s a video on my approach at applying this to agents w @activegraphai: 🆕 ActiveGraph: The Log is the Agent my talk from AI Engineer is live!!! 😆 https://www.youtube.com/watch?v=khVX_BUnEwU it's ab
arXiv:2607.21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user. Existing agent benchmarks often eva
arXiv:2607.11098v2 Announce Type: replace-cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description
WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eval signal that reveals whether an agent fails, and where. The
Pinecone has introduced Nexus, a knowledge engine built specifically for AI agents. Instead of repeatedly searching documents with traditional RAG, Nexus compiles knowledge once from sources like data
arXiv:2607.06101v1 Announce Type: cross Abstract: AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in
Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA ✅ A fully open stack enterprises can own and customize ✅ Benchmark-leadi
This post describes architectural patterns for building a local-first personal AI agent, covering key components including orchestration frameworks, memory systems, tool integration, LangGraph for wor
arXiv:2607.03441v1 Announce Type: cross Abstract: LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previ
Multimodal prompting is clearly the future. I love experimenting with new ways to interact with agents. As a researcher and engineer, I've found that the richer the inputs to the agent and the richer
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason
Some of LangSmith's biggest and most engaged customers trace with: - @aisdk - Claude Agents SDK - OpenAI Agent SDK - No framework at all And I'm sure we'll see tons of http://pi.dev in the near future
Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the app now through Ju
we just released dynamic subagents, which let your agent programmatically orchestrate subagents in a code interpreter. this lets agents do work at scale that tool calls can't reliably handle, like pro
🧑🏫3hr Long Deep Agents Course Great course from a member of the community on Deep Agents Covers task planning, file systems for context management, subagent-spawning, and long-term memory https://www
Agents are easy to demo locally. The hard part is shipping them inside a real app. We published a deployment cookbook for @LangChain agents: full-stack examples with streaming UI, subagents, thread hi
arXiv:2606.09039v1 Announce Type: new Abstract: This study proposes the Behavioral Protocol Framework (BPF), an entropy-controlled pluralistic alignment framework designed to address two critical chal
Just landed nested subagent support in Claude Code Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s releas
arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and
arXiv:2606.02875v1 Announce Type: new Abstract: Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupt
Startup discovery platform @harmonic_ai rebuilt Scout, their AI platform using Deep Agents and LangSmith. Deep Agents: One frontier model + two tool sets (global company data and firm-specific context
arXiv:2602.01053v2 Announce Type: replace Abstract: Role specialization in multi-LLM agent systems is often realized via multi-LoRA, where agents share a pretrained backbone and differ only by lightwe
arXiv:2602.17588v3 Announce Type: replace Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks
new in deepagents: agent rubrics! you define a rubric, and the agent self-evaluates and iterates until it satisfies every rubric criterion. this is similar to /goal in claude code or codex, but more f
arXiv:2605.29442v1 Announce Type: cross Abstract: AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that m
Hermes Agent now can orchestrate the @OpenHandsDev agents with a new optional skill! `hermes update` then do `hermes skills install official/autonomous-ai-agents/openhands` Reminder: You can already d
arXiv:2605.23574v1 Announce Type: new Abstract: Long-horizon language agents can make many plausible local tool calls yet fail to persist until a requested count is actually complete. We study this ga
Most agents die after a few seconds. @AnthropicAI's workshop shows how to build agents that run for hours. full 75-min session with Ash Prabaker & Andrew Wilson. https://www.youtube.com/watch?v=mR-WAv
In this post, you learn how to combine Stream's Vision Agents open-source framework with Amazon Bedrock and Amazon Nova 2 Sonic to build real-time voice agents that can be production-ready in minutes.
Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and s
arXiv:2605.01546v1 Announce Type: cross Abstract: Sixth-generation (6G) networks are increasingly envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unifi
Coding agents are accelerating different types of software work to different degrees. When we architect teams, understanding these distinctions helps us to have realistic expectations. Listing functio
arXiv:2601.01885v2 Announce Type: replace Abstract: Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory mana
arXiv:2506.08332v3 Announce Type: replace Abstract: Machine learning has been widely used to optimize complex engineering workflows across numerous domains. In integrated circuit design, modern flows
APEX-Agents now has a @huggingface leaderboard for open-source models. APEX-Agents is our frontier benchmark for whether models can do the real work of consultants, lawyers, and bankers. https://huggi
Introducing remote agents in Vibe and Mistral Medium 3.5. You can now launch remote agents in the cloud, including from the CLI or Le Chat. Plus, new Work mode in Le Chat for complex, multi-step tasks
arXiv:2604.24020v1 Announce Type: cross Abstract: Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet
Organizational design for agents is hard, benchmarking agents working in concert is hard. Together, this is the next critical frontier for making AI matter in economically valuable tasks, and we reall
the power of open source, open harnesses, open agents, and communities 🔥 super fun to be a part of a community of builders who share cool work like this in the open. also been fun to see builders shar
Ben Thompson / Stratechery: Q&A with Google Cloud CEO Thomas Kurian on building infrastructure for AI agents, balancing internal needs and the demands of customers like Anthropic, and more — This week
arXiv:2411.10109v2 Announce Type: replace Abstract: Machine learning can predict human behavior well when substantial structured data and well-defined outcomes are available, but these models are typi