Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Research shows imitation of expert trajectories breaks weaker models' harness fit, while on-policy expert correction preserves gains across seven enterprise agent tasks.
The paper studies combining automated agent-harness evolution with lightweight fine-tuning across seven enterprise agent tasks using Qwen3-Coder and Gemma 4. Training weaker models on complete expert trajectories under an evolved harness regressed performance by 4-30 points on all tasks, disrupting model-harness fit. The authors propose an on-policy expert-correction pipeline, automated by a meta-level MLE agent, that rewrites only failing turns and preserves the model's planning style.
- Imitation of expert trajectories degrades performance under evolved harnesses
- Regression of 4-30 points across Qwen3-Coder and Gemma 4
- On-policy correction combines harness evolution with model adaptation
- Method targets economical co-evolution for domain-specific enterprise agents
- AI models
- Qwen3-CoderGemma 4
From the original article
1 min read at huggingface.co
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.
By Zhou Yu, Bin Bi, Shiva Kumar Pentyala · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.