EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds

arXiv cs.AIOctober 16, 2026en

arXiv:2610.20786v1 Announce Type: new Abstract: Multi-modal agents have made significant progress in interacting with open worlds. However, their ability to self-evolve remains limited. Supervised fine-tuning enables imitation but not active experience organization, while outcome-based reinforcement learning promotes exploration yet underuses intermediate trajectory information. Therefore, we propose EvolvingBrain, which uses an adaptive skill system as the brain for agent self-evolution, consisting of two following components. Stratified Skill Self-Evolution: extracts Procedural Patterns and Problematic Patterns from model-specific trajectories, summarizes experience by generating skills, a

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter