Recommended, must-read paper on building recursive, self-improving agent harnesses for open-world tasks.
Google paper proposes Harness² for recursive agent harness improvement on open-world tasks
AISummary
Google and Northwestern researchers propose Harness², a framework that improves an agent's harness at test time without ground-truth verifiers. It proposes parallel candidate edits, keeps the best combination, and carries lessons forward to a second harness.
The paper reports gains of up to 11.5 points on WorkBuddy-Bench, 4.5 on JobBench, and 11.8 points on LAB across GLM-5 and Gemini 3.5 Flash.
Post on XView on X
elvisVerified on X
@omarsar0
Learn to build custom harnesses, folks! Here is a highly recommended paper from Google on recursive agent harnessing. Great insights if you work on evolving your harnesses. It also offers an important discussion of recursive self-improvement and evolving harnesses for open-world tasks. They focus on improving your agent harness at test time without a verifier. This allows interesting scaling properties. Harness^2 proposes several edits to the harness for the current task, tests them against each other, and keeps the combination that works best. Lessons from those edits then update a second harness that the agent carries to future tasks. Results: It improved GLM-5 and Gemini 3.5 Flash in every configuration tested across WorkBuddy-Bench, JobBench, and LAB. Running five candidate edits in parallel adds another 2.9 to 3.9 points on WorkBuddy-Bench. ReasoningBank, a memory baseline, fell up to 6.6 points below the base harness on coding tasks in the same comparison. https://arxiv.org/abs/2610.14224 Chat with Paper: https://academy.dair.ai/papers/harness-2-recursive-agent-harnessing-for-an-open-world-2610.14224
Source: elvis · x.comPublished