PILOT在迴圈中：長時域智能體的即時自我改進

摘要

長視野的代理執行會產生經驗，這些經驗既能改善當前執行，也能改善未來工作。大多數自我改進方法僅在執行結束後處理這些經驗，因此無法重新導向正在進行的執行，也無法立即應用並驗證從中所學到的教訓。我們主張自我改進應改為即時進行，利用湧現的經驗既重新導向當前執行，也更新持續存在的執行框架。現有的代理架構無法完全支持這一目標。單代理自我校正將任務執行與軌跡評估結合在同一個情境中，而子代理委派雖然將執行分離，但通常無法重新導向正在運作的子代理。我們提出 PILOT，這是一個監督者-工作者執行框架，透過兩種耦合機制實現即時自我改進：（1）即時引導使獨立的監督者能在執行期間重新導向或中止正在運作的工作者；（2）即時自我演化將執行期間浮現的程序與失敗模式提煉為可重複使用的技能與記憶。在兩個凍結骨幹模型與三個基準測試中，PILOT 在六種配置中的五種中排名第一。在 Terminal-Bench 2.0 上，PILOT 比對應的執行框架高出最多 9.8 個百分點。在自我改進設定中，PILOT 在使用 GLM-5.1 時提升 14.6 分，使用 Kimi-K2.6 時提升 12.4 分。平均輸出詞元分別下降 42.9% 與 47.4%，而每百萬輸出詞元的成功評估次數則分別上升 110.3% 與 134.0%。

English

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.