Google Research 发布 Harness²：智能体自改 harness
Can Agents improve their own harness on unseen tasks? The @GoogleResearch team released Harness², a framework that allows improve an harness around a frozen mod
Google Research 发布 Harness² 框架，让智能体在冻结模型的前提下自行改进 harness。Gemini 3.5 Flash 在 WorkBuddy-Bench 提升 8.4 分、JobBench 提升 7.5 分，并在全部 3 个 benchmark 上均有提升。Skills 与脚本贡献约 50% 的编辑，去掉 skills 会损失 5.3 分。
正文
Can Agents improve their own harness on unseen tasks? The @GoogleResearch team released Harness², a framework that allows improve an harness around a frozen model.
How it works: 1️⃣ Agent runs the base harness on each task to record a baseline trajectory 2️⃣ Editor agent inspects the trajectory, drafts 2 candidate edits (SI, Skills, hooks,….), and runs both. 3️⃣ Composer agent diffs the new trajectory against the baseline, merges edits that fixed failures (within a cap), and runs the final harness. 4️⃣ Reflector agent logs verified lessons into file and saves the winning components to a library for future tasks to pull on demand.
Results: - 💡 Gemini 3.5 Flash +8.4 on WorkBuddy-Bench and +7.5 on JobBench. - 🛠️ Skills and scripts drive ~50% of edits; dropping skills costs 5.3 pts. - 📚 Gemini 3.5 Flash improves on all 3 benchmarks when editing its own harness.