---
id: 20261017-T0-10
title: "EvolvingBrain：让多模态agent在开放世界中自适应自进化"
title_en: "EvolvingBrain: Adaptive Skill System for Multi-modal Agent Self-Evolution"
url: https://ai.daily.yangsir.net/daily/20261017-T0-10
issue_date: 2026-10-17
publish_date: 2026-10-16T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.20786
---

# EvolvingBrain：让多模态agent在开放世界中自适应自进化

多模态agent在开放世界交互方面已有不少进展，但自进化能力仍然有限。监督微调能让agent模仿但无法主动组织经验，基于结果的强化学习也存在局限。EvolvingBrain提出一种自适应技能系统，让多模态agent在开放世界中通过自主组织和演化技能来实现自进化。该方法针对的是agent在陌生环境中持续学习和适应能力的缺失。目前该研究以预印本形式发布在arXiv上。

## English Version

**EvolvingBrain: Adaptive Skill System for Multi-modal Agent Self-Evolution**

Multi-modal agents have made progress in open-world interaction, but their self-evolution capability remains limited. Supervised fine-tuning enables imitation but not active experience organization, and outcome-based reinforcement learning has its own constraints. EvolvingBrain proposes an adaptive skill system that lets multi-modal agents self-evolve in open worlds by autonomously organizing and evolving skills. The method targets the lack of continuous learning and adaptation in unfamiliar environments. The work is available as an arXiv preprint.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.20786)

**详情页**：https://ai.daily.yangsir.net/daily/20261017-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*