外观
论文arXiv 2610.2031214 天前
失败后反思：面向具身空间智能的类脑自进化智能体
原文链接：Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence（arXiv 2610.20312 · 发布日期：2026-10-14）
Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
针对具身空间任务中失败原因难判定的问题，HiMeco通过PEP反思与技能抽象自进化，并在ESI-Bench和EmbSpatial-Bench验证。
核心要点
- 具身空间任务需基于部分视觉证据做复杂多步决策，执行失败原因难以定位。
- HiMeco受元认知监控和海马记忆巩固启发，诊断感知-探索-规划中的失败。
- 方法比较执行尝试以提炼可复用策略，并将交互程序抽象为参数化技能。
- HiMeco在ESI-Bench达到最优表现，并在无进化时提升EmbSpatial-Bench准确率3.94个百分点。
验证范围与局限：验证范围为ESI-Bench和EmbSpatial-Bench，摘要未提及真机验证。
英文摘要 (Abstract)
Vision-Language Models (VLMs) have made substantial progress in spatial reasoning, and self-evolving agents further extend these capabilities to embodied environments by learning from interactions. However, current self-evolution remains particularly challenging in embodied spatial tasks, complex and multi-step decisions from partial visual evidence making it difficult to determine why an execution fails. The failure may stem from misperception, insufficient exploration, or incorrect planning, yet execution feedback alone rarely reveals which component is responsible. As a result, simply accumulating interaction experience can reinforce ineffective strategies. To address this, we propose HiMeco, a brain-inspired self-evolving agent for embodied spatial intelligence, inspired by metacognitive monitoring and hippocampal memory consolidation. Through Hippocampal-Metacognitive Reflection, HiMeco diagnoses failures in perception-exploration-planning (PEP), then compares execution attempts to derive reusable strategies and guidance for avoiding recurring errors. It also abstracts interaction programs into parameterized skills, using evidence contracts and execution-based validation to determine their retention and reuse. These strategies and skills guide subsequent interactions, with memory updated only between rounds and model parameters kept frozen. HiMeco achieves state-of-the-art performance on ESI-Bench, and it also improves accuracy on EmbSpatial-Bench by 3.94 percentage points without evolution.
作者：Xin Li, Xiaohuan Gu, Yifan Wang, Shaobin Ling, Tianli Shi, Jingao Xu, Zhimeng Yin, Dapeng Wu, Yun Wang
来源
本页事实对应的公开页面，以原文为准。