arXiv：cs.AI· Kai Hu, Hua Huang·· 6 小时前
模仿是进化关键：面向自适应智能体的局部修复与可验证技能获取
Imitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents
AI 导读
论文提出被动模仿（PI）架构循环，通过定位被违反的契约、提取局部目标、提出效果匹配技能并对小补丁进行验证，实现智能体的局部修复与技能获取。在十个模拟工具世界中，PI 在允许三次小试验的条件下解决了全部 600 个冷启动留出组合任务，而整轨迹对照仅 6.17%；在未见工具修订上成功率达 70.0%，无小试验时为 24.0%。该实现仅用 CPU，代码与可复现结果已公开。
正文
Abstract:An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation (PI) as an architectural loop that localizes a violated contract, extracts a local goal, proposes an effect-matched skill, tests a small patch, and retains evidence after full-task verification. We instantiate this loop as a deterministic symbolic controller and analyze its finite repair-query complexity under explicit identifiability and noninterference assumptions. Across ten simulated tool worlds, PI solves all 600 cold held-out composition tasks with three allowed small trials, compared with 6.17% for a whole-trajectory control, while an equally expressive compositional repair control matches PI. On an unseen tool revision, PI achieves 70.0% success versus 24.0% without small trials and 79.0% with self-trial enumeration; an exploratory 24-task adaptation stream subsequently raises first-submission success to 100%, supporting a limited correction-and-retention mechanism rather than a unique incentive advantage or general intelligence. The CPU-only implementation, integrity checks, and reproducible results are available at this https URL.
| Comments: | 9 pages,2 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.6 |
| Cite as: | arXiv:2610.16125 [cs.AI] |
| (or arXiv:2610.16125v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16125 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kai Hu [view email]
[v1]
Mon, 12 Oct 2026 03:42:52 UTC (82 KB)
来源：arXiv：cs.AI · arxiv.org