AI 干活时就能边干边改，不用等跑完
现在的 AI 智能体跑长任务，出了错只能等它跑完再复盘，过程里没法拦。这篇提出一个「主管-工人」架构：主管在工人执行途中就能实时叫停、改方向，同时把刚暴露的失败模式提炼成可复用的技能，当场喂回当前任务。在三个基准上，六个配置里拿了五个第一，输出 token 平均省四成多，每百万 token 的成功评估次数翻倍以上。它不是你明天就能装上的东西，但指向一个更本质的变化：AI 的自我改进从「事后总结」变成「边做边学」。
📄 原文摘要(英文)
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent architectures do not fully support this goal. Single-agent self-correction combines task execution and trajectory assessment within one context, while subagent delegation separates execution but typically cannot redirect an active subagent. We present PILOT, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-evolution distils procedures and failure modes revealed during execution into reusable skills and memory. Across two frozen backbones and three benchmarks, PILOT ranks first in five of six configurations. On Terminal-Bench 2.0, PILOT outperforms counterpart harnesses by up to 9.8 percentage points. In the self-improvement setting, PILOT gains 14.6 points with GLM-5.1 and 12.4 points with Kimi-K2.6. Mean output tokens fall by 42.9% and 47.4%, while successful evaluations per million output tokens rise by 110.3% and 134.0%, respectively.