Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modi…

Learn to optimize your own harness, folks. You can squeeze much more performance and value from a harness. This work claims that a self-modified harness matched Codex for 4.03. Specifically, a coding agent rewrote its own harness until it solved 82.0% of Terminal-Bench 2.1 with DeepSeek V4 Flash, without any task reward during the search. The search cost was 4.03. That matches Codex, the top harness in a public nine-harness comparison run under the same settings. SelfSearch has agents modify their own instructions, tools, and procedures using records of earlier self-modification attempts. Each record holds the reasoning, tool actions, and outcomes. The modified agent then becomes the next improver. Population-mean success rises in all six model-benchmark settings, with single agents gaining up to 11.2 points. On SWE-bench Multilingual, one evolved agent gains 5.0 points and spends 38.5% less on tasks both versions solve. Paper: https://arxiv.org/abs/2609.37968 Chat with Paper: https://academy.dair.ai/papers/selfsearch-reward-free-search-for-self-improving-agents-2609.37968

Source: DAIR.AI (X) | 2026-10-05

Related