{"total":15,"papers":[{"id":"arxiv:2606.01770","title":"Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams","date":"2026-06-01","section":"Harness","quality":0.233234,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/e168e03e04c685d889bb8d0c68d63fc7aaa73099093ade681bebd7b2d1069bac/","source_url":"https://arxiv.org/abs/2606.01770","text_available":true},{"id":"arxiv:2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","date":"2026-04-28","section":"Harness","quality":0.085264,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c2358d2261b7478833ca59529278f0f4872896ca5ae4434e8db5d420532e10bd/","source_url":"https://arxiv.org/abs/2604.25850","text_available":true},{"id":"url:github.com/deepseek-ai/deepseek-harness","title":"DeepSeek Harness","date":"2026-08-13","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cccbf88a125b812263afd81c837238d85aaaa257f47b6ceed3e8ad0c1e8d5f34/","source_url":"https://github.com/deepseek-ai/deepseek-harness","text_available":false},{"id":"url:tufalabs.ai/research/duck-harness","title":"Duck Harness: Winning Solution for ARC-AGI-3 Milestone 1 (Tufa Labs)","date":"2026-07-01","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b15badb28c192b3eaa7ff763e7207141406ee559e3b97db13c0226a4cfded614/","source_url":"https://tufalabs.ai/research/duck-harness/","text_available":false},{"id":"arxiv:2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","date":"2026-04-09","section":"Harness","quality":-0.194929,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/392317a8b3bedec8258ff8288d69ac72bc9e60299c5f7bec8962838bb448c2ce/","source_url":"https://arxiv.org/abs/2604.08224","text_available":true},{"id":"url:weco.ai/blog/first-evidence-of-recursive-self-improvement","title":"First evidence of recursive self-improvement (AIDE2, Weco)","date":"2026-07-14","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/00441fa8f2a9743603579837e07f96b97a0a7de239cad14faaccc9aa2e9d770c/","source_url":"https://www.weco.ai/blog/first-evidence-of-recursive-self-improvement","text_available":false},{"id":"url:openai.com/index/harness-engineering","title":"Harness Engineering (OpenAI)","date":"2026-08-25","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a64858f28b8f0c5dd1c3a4da212807c69004781880993ef54e5c383d4c9efbe5/","source_url":"https://openai.com/index/harness-engineering/","text_available":false},{"id":"arxiv:2609.01437","title":"HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?","date":"2026-09-01","section":"Harness","quality":-0.042613,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/0e91a157b5aa6d15aa804a3849a31a55661a73d6c1470ff918d72163f5fe2076/","source_url":"https://arxiv.org/abs/2609.01437","text_available":true},{"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},{"id":"url:alexzhang13.github.io/blog/2026/harness","title":"Language model harnesses are compositional generalizers (Alex Zhang)","date":"2026-07-20","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d724c392cf5eb2db98d9a15e510d13b4220810c062a249c6a02ab86ee1895bb5/","source_url":"https://alexzhang13.github.io/blog/2026/harness/","text_available":false},{"id":"arxiv:2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","date":"2026-03-30","section":"Harness","quality":0.315536,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/8bb0b87384dfdd42c419cf26cc7e52f1f0d89f63afa5d5968e246b73a44c99cb/","source_url":"https://arxiv.org/abs/2603.28052","text_available":true},{"id":"url:github.com/primeintellect-ai/prime-agent","title":"Prime Agent: a self-improving RLM agent (Prime Intellect)","date":"2026-05-08","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/adc0cae9cb95aa146ec2de057eec3396aaa4ad014145497302e36230aefe7e3a/","source_url":"https://github.com/PrimeIntellect-ai/prime-agent","text_available":false},{"id":"url:github.com/alexisfox7/rgb-agent","title":"PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning","date":"2026-07-22","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d9edca36213ad054416ec660f6590afe60c60edd809bcb76c366c99b442cc929/","source_url":"https://github.com/alexisfox7/RGB-Agent","text_available":false},{"id":"url:schema-harness.github.io","title":"Schema: a symbolic world model for ARC-AGI-3","date":"2026-07-17","section":"Harness","quality":null,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/13a6bc75dfa0fc5404345ed01dc0ec698cfd38c08d1ce3c8f4eeb33dfd068e63/","source_url":"http://schema-harness.github.io","text_available":false},{"id":"arxiv:2604.19341","title":"Structured Scaling of AI Discovery Across Diverse Scientific Domains","date":"2026-04-21","section":"Harness","quality":0.65138,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/33ad3375247f86197210840a19064548b997e8617475e606d7a7ac2cda64740e/","source_url":"https://arxiv.org/abs/2604.19341","text_available":true}],"next":null}