让AI自己造工具，而不是用人类给的破工具
现在的AI操作电脑，用的是人类给它配好的工具——就像给你一把螺丝刀去拧所有东西。它想找个函数，可能得把两千行文件全打印出来翻；想填个表格，可能一格一格敲，而不会想到写一行代码。这些工具和“什么时候该用哪个”的判断，全是人手工搭的，新应用一出来就过时。这篇论文干脆让AI自己当工具设计师：一个“元智能体”观察任务智能体干活的过程，不需要知道答案对错，就能总结出该用什么工具、怎么用，存进一个仓库；再用“种群进化”的方式，让不同版本的仓库在没见过的任务上比赛，留下真正管用的。结果很猛：同一个开源模型，配上自己进化出来的工具，在OSWorld V2上的成功率从5.6%涨到21.3%，直接超过了GPT-5.5和Claude Opus 4.8，成本却只有它们的零头。这不是你明天能用的功能，但它指了个方向：AI的进步不一定全靠更大的模型，让AI自己改进自己的操作方式，可能是条更便宜的路。
📄 原文摘要(英文)
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the knowledge of when to use each are built by hand, which cannot keep pace with new applications, workflows, and models. We argue that interface design should itself be an agent capability. We introduce Agent S4, an autonomous computer-use scientist that builds Evolving Agent Interfaces from task experience. A meta-agent examines task agents' trajectories on synthetic training tasks, without success labels, and constructs and revises interfaces and usage knowledge in a repository. Population-based evolution then selects which repositories to develop further by their performance on validation tasks the meta-agent never sees, favoring changes that generalize beyond the seen tasks. On OSWorld V2, Agent S4, with Qwen3.8-27B and the evolved repository of interfaces, sets a new state of the art in open-source computer-use agents, reaching 21.3% binary score, 3.8 times the same model with fixed interfaces. This is above both GPT-5.5 (13.0%) and Claude Opus 4.8 (20.6%), at about 4.3% and 1.5% of their respective costs. On ScienceBoard, the evolved interfaces improve the success rate from 41.4% to 58.6% with the same model. These results suggest that useful interfaces can be evolved from experience, making autonomous interface design a source of improvement complementary to advances in models and harnesses. We open-source our code at https://github.com/simular-ai/agent-s.