Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes a…

Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the model running inside the harness. This is a nice paper from Google showing how to do this co-evolution. Specifically, they propose Evo2, a framework for weight-harness co-evolution. How it works: One policy plays two roles. As a Proposer, it writes edits to its own harness, and as a Reflector, it diagnoses what each edit changed. Those edits and their outcomes then become training data for both roles, using SFT followed by interleaved GRPO. The result: Evo2 reaches 48.3% on SWE-bench Verified and 82.1% on Polyglot, against 41.0% and 62.6% for the strongest baselines. The harness part alone moves a GPT-5-mini agent from 24.4% to 48.3% on SWE-bench Verified. The evolved harnesses also transfer to other benchmarks without further evolution. Paper: https://arxiv.org/abs/2610.13025 Chat with Paper: https://academy.dair.ai/papers/evo-2-evolving-the-evolver-through-weight-harness-co-evolution-2610.13025

Related

• Banger paper from Google on agent harnesses for long-horizon tasks. (bookmark it) Google Research built a many-agent harness for long mathem…
• Must-read paper from Google on self-improving agent harnesses. If you auto-optimize your agent's harness, your eval score can go up while th…
• Nice paper from Salesforce on co-evolving harnesses and models. Harness engineering is a hot topic right now. So this is a great read. (book…

Source: DAIR.AI (X) | 2026-10-13