Knowledge catalogue
arXiv:2606.24595v1 Announce Type: new Abstract: Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, evolving understanding of the user that interactio
arXiv:2509.18371v2 Announce Type: replace-cross Abstract: Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity
pretty sick that i get to work with Jake every day on making continual learning + memory accessible at scale for every single agent one common thread here is...the Trace a large part of Continual Lear
arXiv:2606.24626v1 Announce Type: new Abstract: As autonomous agents tackle increasingly complex multi-step, multi-agent tasks, their execution trajectories have scaled beyond the constraints of even
arXiv:2606.21894v2 Announce Type: replace-cross Abstract: As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineer
arXiv:2606.23743v1 Announce Type: cross Abstract: Modern video diffusion models achieve higher generation quality through scaling, but this also increases inference cost. Although many acceleration me
Nous Research announced that their Hermes Agent has achieved a trillion tokens processed daily and reached 200,000 GitHub stars, reflecting significant adoption and performance milestones for their AI
arXiv:2606.22741v1 Announce Type: new Abstract: Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results i
Hermes Agent has been updated to accept diverse source materials including code repositories, API documentation, manuals, PDFs, and configuration files as input, with the ability to distill and learn
arXiv:2606.12896v2 Announce Type: replace Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention an
Hermes Agent, developed by Nous Research, has expanded its computer use capabilities to support Windows and Linux operating systems in addition to its existing macOS functionality. This enhancement, i
arXiv:2606.12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents
arXiv:2606.11520v1 Announce Type: cross Abstract: Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution
arXiv:2606.10677v1 Announce Type: new Abstract: Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often s
shoutouts: • why multi-agent LLM systems fail? (arXiv:2503.13657) — @mertcemri @melissapan + @istoica05 @matei_zaharia @profjoeyg @adityagp & team • DSPy (arXiv:2310.03714) — @lateinteraction + @hazyr
This is just awesomeness from @cohere, @nickfrosst, and team. I so badly want a coding agent that just runs on my local machine. We are not too far now! Excited to get this to work with my @dair_ai co
arXiv:2606.11042v1 Announce Type: new Abstract: Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely
Also, I found that Hermes Agent + Nemotron 3 Ultra is a mighty combo! Excited to launch a new way to upskill with AI agents. This is how we are making it possible for anyone to learn to build with cod
arXiv:2606.08702v1 Announce Type: new Abstract: Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, y
arXiv:2606.08367v1 Announce Type: cross Abstract: Most evaluations of LLM agents look like exams: a discrete task, a clean environment, a score in minutes or hours. We argue that this approach is mism
arXiv:2605.12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are
// Self-Harness: Harnesses That Improve Themselves // (bookmark this one) Most of the agent scaffolds we rely on today are built once and remain frozen or mostly unchanged. The harness, like the skill
arXiv:2606.09774v1 Announce Type: new Abstract: Advanced scientific simulators expose specialized input languages that turn simulation goals into executable configurations, but learning them can cost
arXiv:2606.08256v1 Announce Type: new Abstract: Verifiability, attribution, and reproducibility are foundational requirements of scientific knowledge, yet current publishing infrastructure does not en
arXiv:2606.08091v1 Announce Type: new Abstract: Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long video genera
arXiv:2601.13508v4 Announce Type: replace-cross Abstract: Autonomous agents are beginning to transform scientific research from tool-assisted workflows toward self-sustaining discovery processes. Comp
arXiv:2606.06976v1 Announce Type: new Abstract: Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct response
Workflow automation vendor Pegasystems Inc. today unveiled a broad set of artificial intelligence enhancements aimed at helping enterprises deploy AI agents in mission-critical business processes whil
The Agent Open: AI's Pickleball Tournament 🏓 Come put your code and backhand to the test and embrace the full Open experience. Custom built out courts. Stadium seating. Exhibition matches by AI leader
OpenEnv is an open-source framework backed by the community for training and developing agentic reinforcement learning systems. The project represents collaborative efforts within the open-source ecos
Release: datasette-agent-edit 0.1a0 I'm planning several plugins for Datasette Agent which can make edits to existing pieces of text - things like collaborative Markdown editing, updating large SQL qu
arXiv:2606.06416v1 Announce Type: cross Abstract: Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updati
arXiv:2606.04484v1 Announce Type: new Abstract: We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks t
arXiv:2606.04051v1 Announce Type: cross Abstract: The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text g
arXiv:2606.05158v1 Announce Type: cross Abstract: Multi-agent reasoning systems adopt a 'generate-then-transfer' paradigm that forces end-to-end latency to scale linearly with pipeline depth. We intro
We have a Fleet agent called @docs_plz in our Slack that's made a very noticeable impact on our velocity of docs changes. In the chart below, you can clearly see that after it was added, the amount of
arXiv:2602.12430v4 Announce Type: replace-cross Abstract: The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) ar
arXiv:2604.17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tas
arXiv:2512.11213v2 Announce Type: replace Abstract: Scaling test-time computation has been shown to significantly improve large language model (LLM) performance without additional training. However, e
Memory has always mattered for personalization and continuity. But as customers move agents from demos into production, another requirement becomes just as important: reliability. Enterprise teams nee
arXiv:2602.08335v2 Announce Type: replace Abstract: Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving com
arXiv:2606.00518v1 Announce Type: new Abstract: Agentic AI systems can plan over multiple steps, use tools, and execute tasks over time. When such systems cause harm, tort law struggles to allocate re
Archestra Inc., a U.K.-based startup whose open-source platform brokers access between artificial intelligence agents and sensitive enterprise data, today announced that it has raised 10 million in ne
arXiv:2602.14849v2 Announce Type: replace-cross Abstract: LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement tri
arXiv:2601.19921v2 Announce Type: replace-cross Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows tha
arXiv:2602.06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scrip
arXiv:2606.01365v1 Announce Type: new Abstract: Tool-using multi-agent large language model (LLM) systems spend computation through model tokens, tool calls, retries, and code execution before produci
arXiv:2606.00660v1 Announce Type: new Abstract: Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a p
arXiv:2606.02483v1 Announce Type: cross Abstract: Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external ser
arXiv:2606.01779v1 Announce Type: new Abstract: LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent
arXiv:2606.02484v1 Announce Type: new Abstract: Recent advances in large language models and agentic AI systems have enabled significant progress in mathematical discovery, from solving competition pr
arXiv:2601.14230v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing syst
arXiv:2606.00619v1 Announce Type: cross Abstract: Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond fin
Todd Bishop / GeekWire: Microsoft unveils Project Solara, an Android-based platform for agent-first devices, with concept hardware and pilots planned at Best Buy, Target, and others — [Editor's Note:
arXiv:2606.02494v1 Announce Type: cross Abstract: Agentic systems entering production typically operate as partially integrated assemblies where structural defects, not task-level errors, dominate the
arXiv:2606.02001v1 Announce Type: new Abstract: General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied
arXiv:2410.02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing
This post documents a parallel experiment where Yohei Nakajima built a coding agent using ActiveGraphAI, showcasing the system's architecture through a flattened event log trace that makes all operati
arXiv:2605.30858v1 Announce Type: new Abstract: Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, tim
arXiv:2605.31318v1 Announce Type: new Abstract: Modeling an opponent's intent is critical for effective decision-making in non-cooperative, competitive, and general-sum multi-agent reinforcement learn