Learning from Research: Toward Lifelong Agent Harness Evolution
- Published
- Source
- arXiv
- Paper number
- 1143
- Field
- AI / Agents
- arXiv ID
- 2609.40169
Key points
- The approach keeps model weights fixed and lets the agent evolve its harness (the software wrapping it) by learning from research papers.
- Motivated by the passivity of execution-feedback-only methods, it proactively extracts improvement strategies from the research literature.
- It builds a pipeline that uses topic modeling to find strategies in papers and experiments with their combinations to select the best.
- Task goal completion improved from 49.6% to 63.6% on AppWorld and from 72.7% to 81.9% on Tau2-Bench Telecom.
Paper links
External research summaries. These are not HDATF publications or measured product results.