# PILOT 框架实现智能体运行中实时自我改进

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-31 11:05
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmtgo54vy04g6roch8yhwdo6r
- 原文链接：https://x.com/rohanpaul_ai/status/2094260136457982023

## AI 摘要

新论文提出 PILOT 框架，让智能体在任务运行中实时自我改进，而非等运行结束后才学习。监督者实时观察工作进程、可引导或中止，并将经验写入持久技能与记忆。在 6 项模型基准配置中 5 项排名第一，GLM-5.1 与 Kimi-K2.6 在 Terminal-Bench 2.0 上最佳通过率分别提升 14.6 和 12.4 个百分点，输出 token 量下降 42.9% 和 47.4%。

## 正文

Most agent self-improvement happens too late: the system learns from a run only after that run is already over.

This new paper, moves that learning inside the run with PILOT, the harness.

A worker handles the task while a separate supervisor watches its trajectory, can steer or abort it, and writes useful procedures or failure modes into persistent skills and memory.

That division lets the worker focus on execution while the supervisor keeps a cleaner view of the goal, progress, and drift.

Using the same frozen backbone for every system, PILOT ranked 1st in 5 of 6 model-benchmark configurations. Across 20 Terminal-Bench 2.0 self-improvement iterations, its best observed pass rate improved by 14.6 percentage points with GLM-5.1 and 12.4 with Kimi-K2.6. Mean output tokens per evaluated task fell 42.9% and 47.4%, respectively.

For long-horizon agents, that changes the self-improvement loop: a lesson does not have to wait for the next rollout. It can recover the current attempt, get tested immediately, and become part of the system used by later workers.

– arxiv. org/abs/2608.26530

Title: "PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents"