Agents
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
arXiv:2609.02094v1 Announce Type: new Abstract: LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging.
arXiv:2609.02094v1 Announce Type: new Abstract: LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection methods build experience memories, but memories are mostly hard to invoke, refine, or scale, while agent skills offer a more actionable unit: structured procedural knowledge that specifies when to act, how to act, and which resources or tools to use. We introduce MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills. MASkills presents a new agent-optimization pipeline that integrates skill-conditioned credit assignment, hierarchical credit aggregation, and momentum-smoothed optimization, enabling agent skill libraries to evolve through refinement, induction, consolidation, and pruning. Experiments on HotpotQA, LoCoMo, and GAIA demonstrate the effectiveness of MASkills across multiple agentic tasks. Our code is available at https://github.com/DaRL-GenAI/MASkills
Related
- MARFT: Multi-Agent Reinforcement Fine-Tuning
- Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
- Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
- Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
Source: arXiv cs.AI | 2026-09-03