AI 中文总结
该研究针对长智能体自我改进方法无法实时利用经验的问题，提出PILOT框架，通过实时引导与实时自我进化机制，在多基准测试中取得显著性能提升。
AI 中文摘要
长时程智能体运行会产生可改进当前运行及后续工作的经验。大多数自我改进方法仅在执行结束后处理这些经验，因此无法重定向正在进行的运行，也无法立即应用和验证从该运行中获得的经验。我们认为自我改进应是实时的，利用不断涌现的经验既重定向正在进行的运行，又更新持久的框架。现有智能体架构无法完全支持这一目标：单智能体自我修正在同一上下文内结合任务执行与轨迹评估，而子智能体委派虽分离了执行，但通常无法重定向正在进行的子智能体。我们提出PILOT，一种用于实时自我改进的监督者-工作者框架，包含两个耦合机制：（1）实时引导，允许单独的监督者在执行期间重定向或中止正在进行的工作者；（2）实时自我进化，将执行期间揭示的过程和失败模式提炼为可复用的技能与记忆。在两个冻结的骨干模型和三个基准测试中，PILOT在6种配置里的5种排名第一；在Terminal-Bench 2.0上，PILOT比同类框架的性能高出最多9.8个百分点。在自我改进设置中，PILOT使用GLM-5.1时提升14.6个百分点，使用Kimi-K2.6时提升12.4个百分点；平均输出令牌数分别下降42.9%和47.4%，每百万输出令牌的成功评估数分别提升110.3%和134.0%。
英文摘要
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.
