{"id":"url:lilianweng.github.io/posts/2026-07-04-harness","title":"Harnesses for models (Lilian Weng, 2026)","date":"2026-07-04","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c1ea249334ba128a9fff468e25fa4f8d13d4cccd13661ee130bec020ebb6463b/","source_url":"https://lilianweng.github.io/posts/2026-07-04-harness/","text_available":false,"authors":["Lilian Weng"],"outgoing":[{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2303.17651","evidence":"id","id":"arxiv:2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/accef2157d87cf33be93cb3a9af246528b0a3742a9e2e700a194956fac8f5cf4/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2309.16797","evidence":"id","id":"arxiv:2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/daac3bcfcd7f39084d995905e9ef96ae01c5aab7bfe8e565bd7622b4e44088f7/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2408.08435","evidence":"id","id":"arxiv:2408.08435","title":"Automated Design of Agentic Systems","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c9890d5668d1c1b33e29569b74626fd586f456af6a97c657b8c99895c90f59a5/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2410.07095","evidence":"id","id":"arxiv:2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/f0a0c6321ec079098a36ad19b3900d77197a3af1f6bbf6eee8a083e5eb03d42e/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2505.22954","evidence":"id","id":"arxiv:2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c29f716871f80314868b5647692de387f26e12166b93bd362915fd272b6e081c/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2507.19457","evidence":"id","id":"arxiv:2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c1ef72d96fa3292590a6a3d112ab509840081b59aaa771cf42b8b0e8ef62ba08/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2601.16175","evidence":"id","id":"arxiv:2601.16175","title":"Learning to Discover at Test Time","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d0b45cbbc72945765e689cbfb7ac7e4e92dfbb764861b27682ac0744ef05b70/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2601.21557","evidence":"id","id":"arxiv:2601.21557","title":"Meta Context Engineering via Agentic Skill Evolution","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/bedaeecadf58846f4728c50c03396fc96ba18429ecf14052b4c5e177394a246e/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2603.19461","evidence":"id","id":"arxiv:2603.19461","title":"Hyperagents","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/17eec8a15debc212b5530f117dd8ba8bad339590729cbbc4f75a47755ebcb544/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2603.28052","evidence":"id","id":"arxiv:2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bb0b87384dfdd42c419cf26cc7e52f1f0d89f63afa5d5968e246b73a44c99cb/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"arxiv:2604.25850","evidence":"id","id":"arxiv:2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c2358d2261b7478833ca59529278f0f4872896ca5ae4434e8db5d420532e10bd/"},{"source":"url:lilianweng.github.io/posts/2026-07-04-harness","target":"url:sakana.ai/shinka-evolve","evidence":"id","id":"url:sakana.ai/shinka-evolve","title":"ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a13eace17f3407cb1634b579b2738f15f1e035897a8f1842305198c6d2bf35e1/"}],"incoming":[],"text_parts":[],"contents":[],"text_code_points":0,"source_markdown":null}