{"slug": "co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch", "title": "Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails", "summary": "Automated harness evolution can let smaller models match frontier-model performance on domain-specific agentic tasks at a fraction of the cost, according to research on co-evolving harnesses and models. The work finds that on-policy correction helps weaker models catch up in cases where imitation fails, with agent harnesses — the system prompt, tool set, execution hooks, and context-management scaffolding around a model — identified as a critical determinant of agentic task success.", "body_md": "Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. S", "url": "https://wpnews.pro/news/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch", "canonical_source": "https://aiflash.com/news/116788/", "published_at": "2026-09-10 04:00:12+00:00", "updated_at": "2026-09-10 04:21:34.302077+00:00", "lang": "en", "topics": ["ai-agents", "ai-research", "large-language-models", "ai-tools"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch", "markdown": "https://wpnews.pro/news/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch.md", "text": "https://wpnews.pro/news/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch.txt", "jsonld": "https://wpnews.pro/news/co-evolving-harnesses-and-models-on-policy-correction-helps-weaker-models-catch.jsonld"}}