AI RESEARCH
ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolution
arXiv CS.AI
•
ArXi:2602.02709v3 Announce Type: replace Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To address this limitation, our primary contribution is ATLAS (Adaptive Task-distributed Learning for Agentic Self-evolution), a multi-agent framework where specialized meta-agents collaboratively train and refine an active agent toward a domain-specific policy.