Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence· Reflect After Failure: 受脑启发的自我进化的具身空间智能体
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 metacogniti
提出受脑启发的自进化智能体HiMeco，解决具身空间任务中的执行失败问题。
- 核心方法
- HiMeco通过模仿人脑元认知机制，在失败后反思，识别失败原因（如感知错误、探索不足或规划不当），并针对性地调整策略。
- 适合谁读
- 研究者，特别是关注具身智能和自进化学习领域的研究者
- 要解决的问题
- 当前自进化智能体在面对需要复杂和多步骤决策的具身空间任务时难以从执行失败中有效学习。
- 关键实验
- 在多个具身空间任务中进行了实验，展示了HiMeco相比于现有方法在成功率和学习效率上的提升。
- 主要贡献
- 实现了更高效的自进化学习，减少了无效策略的强化，提高了复杂具身空间任务的成功率。
- 意义与局限
- 为具身智能体提供了一种新的学习机制，具有广泛的应用前景，但目前仅限于模拟环境中的验证，实际应用还需进一步研究。