{"slug": "evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in", "title": "EvolvingBrain: An Adaptive Skill System for Multi-modal Agents Self-Evolution in Open Worlds", "summary": "Researchers propose EvolvingBrain, an adaptive skill system that lets multi-modal agents self-evolve in open worlds by extracting Procedural and Problematic Patterns from model-specific trajectories and organizing them into a Stratified Skill Architecture of Domain, Plan, and Action/Trap Skills. The system's State-Aware Adaptive Execution summarizes long-horizon interactions into Structured Abstractive Memory that guides a State-Aware Skill Fusion Strategy, and experiments on VAB-Minecraft and DiscoveryWorld show improved success rates on open-world tasks plus generalization capabilities. Code is provided in the paper's supplementary materials and will be publicly released in the camera-ready version.", "body_md": "arXiv:2610.20786v1 Announce Type: new \nAbstract: 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, and evolves through multiple interactions with the open world, ultimately forming a Stratified Skill Architecture consisting of Domain, Plan, and Action/Trap Skills, which provides the agent with a multi-granularity knowledge repository and a novel evolution approach. State-Aware Adaptive Execution: summarizes long-horizon interactions into Structured Abstractive Memory and uses it to guide the State-Aware Skill Fusion Strategy, enabling the agent to utilize knowledge according to its current state. Experiments on VAB-Minecraft and DiscoveryWorld demonstrate that EvolvingBrain improves success rates on open-world tasks and exhibits generalization capabilities. Our code is provided in the supplementary materials and will be publicly released in the camera-ready version.", "url": "https://wpnews.pro/news/evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in", "canonical_source": "https://arxiv.org/abs/2610.20786", "published_at": "2026-10-16 04:00:00+00:00", "updated_at": "2026-10-16 05:05:52.884627+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "machine-learning"], "entities": ["EvolvingBrain", "VAB-Minecraft", "DiscoveryWorld", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in", "markdown": "https://wpnews.pro/news/evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in.md", "text": "https://wpnews.pro/news/evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in.txt", "jsonld": "https://wpnews.pro/news/evolvingbrain-an-adaptive-skill-system-for-multi-modal-agents-self-evolution-in.jsonld"}}