[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-ai-agent-papers-worth-tracking-en":3,"article-related-ai-agent-papers-worth-tracking-en":33,"series-industry-c54028b3-3c5f-4c00-9c7f-4b8932c74f2d":80},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":25,"views":29,"created_at":30,"published_at":31,"topic_cluster_id":32},"c54028b3-3c5f-4c00-9c7f-4b8932c74f2d","ai-agent-papers-worth-tracking-en","AI agent papers worth tracking in one repo","\u003Cp data-speakable=\"summary\">This repo curates \u003Ca href=\"\u002Ftag\u002Fai-agent\">AI agent\u003C\u002Fa> papers by theme so you can scan the field fast.\u003C\u002Fp>\n\u003Cp>This \u003Ca href=\"\u002Ftag\u002Fgithub\">GitHub\u003C\u002Fa> collection tracks AI \u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> research in themed buckets and updates it biweekly, with 1,494 stars showing strong community use. If you want a fast way to follow planning, \u003Ca href=\"\u002Ftag\u002Fskills\">skills\u003C\u002Fa>, harnesses, and surveys without reading every arXiv feed, this list shows where to start.\u003C\u002Fp>\n\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>Item\u003C\u002Fth>\u003Cth>What it covers\u003C\u002Fth>\u003Cth>Example signals\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Harness\u003C\u002Ftd>\u003Ctd>Runtime structure for agent execution\u003C\u002Ftd>\u003Ctd>Safety, search, production workflows\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Skills\u003C\u002Ftd>\u003Ctd>Reusable agent abilities\u003C\u002Ftd>\u003Ctd>Skill creation, governance, evaluation\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Survey\u003C\u002Ftd>\u003Ctd>Field overviews\u003C\u002Ftd>\u003Ctd>Taxonomy, trends, benchmarks\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Architecture\u003C\u002Ftd>\u003Ctd>How agents are organized\u003C\u002Ftd>\u003Ctd>Single-agent, multi-agent, ops\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Applications\u003C\u002Ftd>\u003Ctd>Where agents are used\u003C\u002Ftd>\u003Ctd>Web, software, data, research\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2>1. Harness papers for runtime design\u003C\u002Fh2>\n\u003Cp>The harness section is the best entry point if you care about how agents actually run in production. It gathers papers on execution substrates, safety checks, search behavior, and architecture patterns, which makes it useful for builders who need more than model prompts.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781744566857-bxx8.png\" alt=\"AI agent papers worth tracking in one repo\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\n\u003Cp>Representative papers in this bucket include \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.13357\">AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.15184\">Is Grep All You Need? How Agent Harnesses Reshape Agentic Search\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.27922v1\">Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cul>\u003Cli>Focuses on execution, not just prompting\u003C\u002Fli>\u003Cli>Useful for agent ops, evaluation, and safety work\u003C\u002Fli>\u003Cli>Includes survey and benchmark entries\u003C\u002Fli>\u003C\u002Ful>\n\u003Ch2>2. Skills papers for reusable agent abilities\u003C\u002Fh2>\n\u003Cp>If your interest is what agents can learn to do repeatedly, the skills section is the most practical cluster. It covers skill creation, selection, governance, and self-evolution, so you can compare papers that treat skills as modular parts of an agent system.\u003C\u002Fp>\n\u003Cp>That makes it a strong fit for teams building long-lived agents. Papers such as \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.06614\">SkillOS: Learning Skill Curation for Self-Evolving Agents\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.18401\">SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.27760\">SkillGrad: Optimizing Agent Skills Like Gradient Descent\u003C\u002Fa> show how broad the topic has become.\u003C\u002Fp>\n\u003Ccode>Skill themes you will see here:\n- skill generation\n- skill memory and management\n- least-privilege enforcement\n- skill evaluation\n- self-evolving skill systems\u003C\u002Fcode>\n\u003Ch2>3. Survey papers for fast field orientation\u003C\u002Fh2>\n\u003Cp>The survey bucket is the quickest way to understand where the research is going. Instead of one method, these papers map taxonomies, techniques, and open questions, which is helpful when you need a clean overview before choosing a subtopic.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781744562845-afjp.png\" alt=\"AI agent papers worth tracking in one repo\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\n\u003Cp>For a broad starting point, \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.07358\">A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2605.02913\">Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning\u003C\u002Fa> show the repository’s survey style. The collection also points to related work on collaboration, failure attribution, and self-evaluation.\u003C\u002Fp>\n\u003Cul>\u003Cli>Good for literature reviews and slide prep\u003C\u002Fli>\u003Cli>Helps identify subfields worth deeper reading\u003C\u002Fli>\u003Cli>Pairs well with benchmark papers\u003C\u002Fli>\u003C\u002Ful>\n\u003Ch2>4. Architecture papers for agent system design\u003C\u002Fh2>\n\u003Cp>The architecture section organizes papers around single-agent, multi-agent, and agent-ops patterns. That is useful if you are deciding how to structure a product, because the papers here are about system shape as much as model behavior.\u003C\u002Fp>\n\u003Cp>Use this section when you need to compare coordination styles or operational patterns. The repo’s links make it easy to jump from broad architecture choices to more specific application areas like digital agents or enterprise agents.\u003C\u002Fp>\n\u003Cul>\u003Cli>Single-agent setups for focused tasks\u003C\u002Fli>\u003Cli>Multi-agent setups for coordination and division of labor\u003C\u002Fli>\u003Cli>Agent-ops and UX for production deployment\u003C\u002Fli>\u003C\u002Ful>\n\u003Ch2>5. Application papers for domain-specific use cases\u003C\u002Fh2>\n\u003Cp>The application sections are where the repository becomes especially useful for practitioners. Instead of staying abstract, it sorts papers into embodied, web, mobile, software, data, research, API, deep research, enterprise, and finance agents.\u003C\u002Fp>\n\u003Cp>That lets you jump straight to the environment you care about. If you are building a browser worker, a coding assistant, or a research \u003Ca href=\"\u002Ftag\u002Fcopilot\">copilot\u003C\u002Fa>, the application pages narrow the reading list quickly and reduce time spent on irrelevant papers.\u003C\u002Fp>\n\u003Ccode>Examples of application clusters:\n- Web agents\n- GUI agents\n- Software agents\n- Research agents\n- Enterprise agents\u003C\u002Fcode>\n\u003Ch2>How to decide\u003C\u002Fh2>\n\u003Cp>Pick harness papers if you care about execution and safety, skills papers if you want reusable capabilities, surveys if you need orientation, and architecture or application papers if you are building a system for a specific setting. For most readers, the fastest path is survey first, then harness or skills, then the application area that matches the product.\u003C\u002Fp>\n\u003Cp>Because the repo is updated biweekly, it works well as a living reading list rather than a one-time roundup.\u003C\u002Fp>","A curated repo of 4 agent paper themes helps you find planning, skills, harnesses, and surveys fast.","github.com","https:\u002F\u002Fgithub.com\u002Fmasamasa59\u002Fai-agent-papers",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781744566857-bxx8.png","industry","en","2455fdb3-eaa3-475a-a1e7-1cd98a1c6128",[17,18,19,20,21,22,23,24],"AI agents","papers","GitHub","survey","harness","skills","architecture","applications",[26,27,28],"The repo is a biweekly curated index of AI agent research.","Harness and skills are the most practical sections for builders.","Surveys, architecture, and application buckets help readers narrow the field fast.",0,"2026-06-18T01:02:21.922628+00:00","2026-06-18T01:02:21.912+00:00","d19fc184-5852-4c4d-9ec0-db0c4841ac17",{"tags":34,"relatedLang":39,"relatedPosts":43},[35,37],{"name":19,"slug":36},"github",{"name":17,"slug":38},"ai-agents",{"id":15,"slug":40,"title":41,"language":42},"5-ai-agent-papers-worth-tracking-zh","5 個值得追蹤的 AI agent 論文主題","zh",[44,50,56,62,68,74],{"id":45,"slug":46,"title":47,"cover_image":48,"image_url":48,"created_at":49,"category":13},"8d054c0f-5009-487a-91d9-8e364934b572","90-minute-takedown-turns-ai-ops-into-crisis-en","A 90-minute takedown turns AI ops into crisis","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781759006326-hpkw.png","2026-06-18T05:02:57.643178+00:00",{"id":51,"slug":52,"title":53,"cover_image":54,"image_url":54,"created_at":55,"category":13},"0802f58b-dd51-4bae-8881-4f873ed99eb0","gpt-56-fix-and-upgrade-release-en","GPT-5.6 looks like a fix-and-upgrade release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781756270916-jh5e.png","2026-06-18T04:17:28.410175+00:00",{"id":57,"slug":58,"title":59,"cover_image":60,"image_url":60,"created_at":61,"category":13},"8f8d8771-bdbf-43b6-aae5-121514dc88dd","anthropic-paid-ai-monetization-path-en","Anthropic 的付费 AI 落地路径","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781755369794-t0l0.png","2026-06-18T04:02:26.075911+00:00",{"id":63,"slug":64,"title":65,"cover_image":66,"image_url":66,"created_at":67,"category":13},"9ecca76d-faf4-42c7-bd45-26dc933d98e8","github-hottest-repos-ai-agent-tools-en","GitHub’s hottest repos are AI agent tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781754467751-karc.png","2026-06-18T03:47:22.951804+00:00",{"id":69,"slug":70,"title":71,"cover_image":72,"image_url":72,"created_at":73,"category":13},"0d5b1c95-78d2-4ec1-9834-16349c40e3ac","anthropic-fable-shows-ai-can-outsmart-constraints-en","Anthropic’s Fable shows AI can outsmart constraints","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781751780406-molv.png","2026-06-18T03:02:34.017492+00:00",{"id":75,"slug":76,"title":77,"cover_image":78,"image_url":78,"created_at":79,"category":13},"65eefaf5-e319-4bb7-b647-f563c584d2c9","openai-partner-network-delivery-strategy-en","OpenAI’s partner network is a delivery strategy, not a logo program","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781741863531-fdio.png","2026-06-18T00:17:19.295463+00:00",[81,86,91,96,101,106,111,116,121,126],{"id":82,"slug":83,"title":84,"created_at":85},"d35a1bd9-e709-412e-a2df-392df1dc572a","ai-impact-2026-developments-market-en","AI's Impact in 2026: Key Developments and Market Shifts","2026-03-25T16:20:33.205823+00:00",{"id":87,"slug":88,"title":89,"created_at":90},"5ed27921-5fd6-492e-8c59-78393bf37710","trumps-ai-legislative-framework-en","Trump's AI Legislative Framework: What's Inside?","2026-03-25T16:22:20.005325+00:00",{"id":92,"slug":93,"title":94,"created_at":95},"e454a642-f03c-4794-b185-5f651aebbaca","nvidia-gtc-2026-key-highlights-innovations-en","NVIDIA GTC 2026: Key Highlights and Innovations","2026-03-25T16:22:47.882615+00:00",{"id":97,"slug":98,"title":99,"created_at":100},"0ebb5b16-774a-4922-945d-5f2ce1df5a6d","claude-usage-diversifies-learning-curves-en","Claude Usage Diversifies, Learning Curves Emerge","2026-03-25T16:25:50.770376+00:00",{"id":102,"slug":103,"title":104,"created_at":105},"69934e86-2fc5-4280-8223-7b917a48ace8","openclaw-ai-commoditization-concerns-en","OpenClaw's Rise Raises Concerns of AI Model Commoditization","2026-03-25T16:26:30.582047+00:00",{"id":107,"slug":108,"title":109,"created_at":110},"b4b2575b-2ac8-46b2-b90e-ab1d7c060797","google-gemini-ai-rollout-2026-en","Google's Gemini AI Rollout Extended to 2026","2026-03-25T16:28:14.808842+00:00",{"id":112,"slug":113,"title":114,"created_at":115},"6e18bc65-42ae-4ad0-b564-67d7f66b979e","meta-llama4-fabricated-results-scandal-en","Meta's Llama 4 Scandal: Fabricated AI Test Results Unveiled","2026-03-25T16:29:15.482836+00:00",{"id":117,"slug":118,"title":119,"created_at":120},"bf888e9d-08be-4f47-996c-7b24b5ab3500","accenture-mistral-ai-deployment-en","Accenture and Mistral AI Team Up for AI Deployment","2026-03-25T16:31:01.894655+00:00",{"id":122,"slug":123,"title":124,"created_at":125},"5382b536-fad2-49c6-ac85-9eb2bae49f35","mistral-ai-high-stakes-2026-en","Mistral AI: Facing High Stakes in 2026","2026-03-25T16:31:39.941974+00:00",{"id":127,"slug":128,"title":129,"created_at":130},"9da3d2d6-b669-4971-ba1d-17fdb3548ed5","cursors-meteoric-rise-pressures-en","Cursor's Meteoric Rise Faces Industry Pressures","2026-03-25T16:32:21.899217+00:00"]