The fastest-moving corner of AI, tracked live: the research, frameworks, models, and launches driving autonomous systems forward. Auto-refreshes throughout the day.
Title-anchored arXiv search, so results are actually about agents.
Repos tagged ai-agents on GitHub, active in the last 60 days.
Latest releases from the agent frameworks most people build on.
Trending agent-oriented models on the Hugging Face Hub.
Trending agent Spaces you can run in the browser right now.
Agent projects shown on Hacker News in the past two weeks.
Top Hacker News discussions specifically about AI agents.
The latest Agentic AI writing from the community (Medium doesn't expose clap counts, so this is newest-first, not vote-ranked).
Lab blog posts whose titles mention agents.
Oct 26
Frontier multimodal large language models (MLLMs) can control robots without robot-specific training, but how their capabilities compare and interact with post-trained vision-language-action (VLA) and world action model…
Oct 26
A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introduce Zero-real Agent Policy (ZAP), a recipe that teaches a…
Oct 26
Deep research, or any use of large language models (LLMs) to read a large document collection and produce insights, requires synthesizing information from different sources. In this work, we find that LLMs produce long-…
Oct 26
Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing e…
Oct 26
Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own dat…
Oct 26
Multi-objective multi-agent reinforcement learning (MOMARL) addresses agent coordination and objective trade-offs simultaneously while optimising overall system performance. Existing work tends to treat multi-agent coop…
Oct 26
Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the weaknesses are fixed. We study how to apply error…
Oct 26
Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interaction rounds, and skills. However, the resulting configuration space gro…
Reverse engineer anything with agents, from app behavior down to native binaries.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor…
DeepSeek Harness: Everything is a Plugin.
The agent that grows with you
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemin…
All-Hands-AI/OpenHands
browser-use/browser-use
0.13.14: Python agent and integration updates
crewAIInc/crewAI
langchain-ai/langchain
openai/openai-agents-python
microsoft/autogen
image text to text
text generation
text generation
image text to text
text generation
image text to text
text generation
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Live demo
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Show HN
Tom Otto
Tuhin
Alain Airom (Ayrom)
Robert Hjertmann Christiansen
Alvaro Leandro Cavalcante Carneiro
Ferhat Yildiz
Abhishekjambla
Eylon Steiner
Eylon Steiner