<span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{&quot;user&quot;:&quot;librarian-bot&quot;}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</p>\n","updatedAt":"2026-05-29T06:19:38.489Z","author":{"_id":"5fad8602b8423e1d80b8a965","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fad8602b8423e1d80b8a965/tRqTwcZmrGka8c1vFq2wX.jpeg","fullname":"Victor Gallego","name":"vicgalle","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":144,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7918877601623535},"editors":["vicgalle"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/5fad8602b8423e1d80b8a965/tRqTwcZmrGka8c1vFq2wX.jpeg"],"reactions":[],"isReport":false}},{"id":"6a1a4194ca63123d87cf1bd8","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":359,"isUserFollowing":false},"createdAt":"2026-05-30T01:47:00.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [PACE: Two-Timescale Self-Evolution for Small Language Model Agents](https://huggingface.co/papers/2605.23019) (2026)\n* [AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models](https://huggingface.co/papers/2604.22871) (2026)\n* [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://huggingface.co/papers/2604.25850) (2026)\n* [Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use](https://huggingface.co/papers/2605.02964) (2026)\n* [Continual Harness: Online Adaptation for Self-Improving Foundation Agents](https://huggingface.co/papers/2605.09998) (2026)\n* [RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets](https://huggingface.co/papers/2604.04347) (2026)\n* [Workspace Optimization: How to Train Your Agent](https://huggingface.co/papers/2605.09650) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2605.23019\">PACE: Two-Timescale Self-Evolution for Small Language Model Agents</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.22871\">AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.25850\">Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.02964\">Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.09998\">Continual Harness: Online Adaptation for Self-Improving Foundation Agents</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.04347\">RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.09650\">Workspace Optimization: How to Train Your Agent</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{&quot;user&quot;:&quot;librarian-bot&quot;}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-05-30T01:47:00.407Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":359,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7114922404289246},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.30003","authors":[{"_id":"6a192fdb56b4bb14ec65d0f2","user":{"_id":"5fad8602b8423e1d80b8a965","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fad8602b8423e1d80b8a965/tRqTwcZmrGka8c1vFq2wX.jpeg","isPro":false,"fullname":"Victor Gallego","user":"vicgalle","type":"user","name":"vicgalle"},"name":"Víctor Gallego","status":"claimed_verified","statusLastChangedAt":"2026-05-29T08:49:28.877Z","hidden":false}],"publishedAt":"2026-05-28T00:00:00.000Z","submittedOnDailyAt":"2026-05-29T00:00:00.000Z","title":"Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas","submittedOnDailyBy":{"_id":"5fad8602b8423e1d80b8a965","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fad8602b8423e1d80b8a965/tRqTwcZmrGka8c1vFq2wX.jpeg","isPro":false,"fullname":"Victor Gallego","user":"vicgalle","type":"user","name":"vicgalle"},"summary":"We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent R (run as a coding agent) reads the inner-loop source code, edits system prompts, feedback functions, helper libraries, and iteration logic, runs evaluations, and decides what to keep, following the autoresearch paradigm. Across two games (Cleanup and Gathering), two policy-synthesizer LLMs, and two welfare objectives (utilitarian efficiency and Rawlsian maximin), the researcher reliably exceeds hand-designed baselines, sharply tightens run-to-run variance, and outperforms prompt-only optimization. The discovered pipelines are objective-dependent: only under maximin does the researcher inject an explicit fairness mechanism into synthesizer pipelines, a class of mechanism that is absent from its own objective-agnostic system prompt and from every efficiency-optimized pipeline. This supports an information-design reading in which the researcher chooses what to reveal to the boundedly rational synthesizer as a function of the welfare objective. Code at https://github.com/vicgalle/autoresearch-social-dilemmas.","upvotes":1,"discussionId":"6a192fdc56b4bb14ec65d0f3","githubRepo":"https://github.com/vicgalle/autoresearch-social-dilemmas","githubRepoAddedBy":"user","ai_summary":"Two-level autoresearch framework enables AI agents to autonomously optimize LLM policy-synthesis pipelines for multi-agent social dilemmas, demonstrating superior performance and objective-specific mechanism discovery.","ai_keywords":["autoresearch","LLM policy-synthesis","multi-agent Sequential Social Dilemmas","researcher agent","inner-loop pipeline","outer-loop AI agent","policy-synthesizer","welfare objectives","utilitarian efficiency","Rawlsian maximin","boundedly rational synthesizer","information-design"],"githubStars":1},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"5fad8602b8423e1d80b8a965","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fad8602b8423e1d80b8a965/tRqTwcZmrGka8c1vFq2wX.jpeg","isPro":false,"fullname":"Victor Gallego","user":"vicgalle","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.30003.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.30003 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.30003 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.30003 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.