Turbo Harness: Instance-Adaptive Harness Optimization
- Published
- Source
- arXiv
- Paper number
- 1144
- Field
- AI / Agents
- arXiv ID
- 2609.40330
Key points
- The work starts from the observation that a globally optimized harness tuned to the average may not be optimal for every task instance.
- It recycles byproducts from a finished optimization run into a structured playbook, avoiding the cost of re-running expensive search.
- A harness editor referencing the playbook generates instance-specific patches, so the execution model runs in a tailored environment.
- It consistently outperformed existing harness optimization methods across 7 benchmarks covering interactive agents, software engineering, and long-horizon terminal tasks.
Paper links
External research summaries. These are not HDATF publications or measured product results.