AI 学会给自己升级工具了
大模型的能力不只取决于模型本身，还取决于它外面那层「工具壳」——怎么调用、怎么查资料、怎么组织步骤。以前这层壳是人手写的，这篇让 AI 自己改自己的壳：先提出几种改法，再在任务上试，选效果好的，然后把经验存下来，下次遇到新任务直接套用。在三个专业基准上，单次自我升级就让 GLM-5 和 Gemini 3.5 Flash 的得分最高涨了 11.8 个百分点。它不是你明天能用上的东西，但它指向一个方向：AI 不再只是被人类调教，而是开始自己给自己调教。
📄 原文摘要(英文)
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses. However, deploying RSI in open-world settings still faces two critical challenges. First, open-world tasks are typically unseen during the harness design phase and novel at test time, leaving no ground-truth verifiers to reliably guide online harness edits. Second, the RSI process remains highly task-specific and fails to generalize to novel scenarios. We introduce Harness^2, a plug-and-play, recursive agent harnessing framework that addresses these challenges through two connected levels of recursion. Task-level recursion refines the current task's harness using a contrastive Propose-Probe-Compose step that reliably guides edits without ground-truth verifiers, and can be scaled further via parallel or sequential recursion. Harnessing-level recursion then extracts experience from these edits to update a continual improvement harness, enabling the agent to better adapt to future tasks. Across three professional benchmarks and four model-harness configurations, a single step consistently improves GLM-5 and Gemini 3.5 Flash over their base harnesses, yielding gains of up to 11.5 points on WorkBuddy-Bench, 4.5 points on JobBench, and 11.8 percentage points on LAB, with further gains as the task-level recursion budget increases.