Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

This work studies how joint alignment tuning can reduce capability gaps among large language model based agents and improve coordination in multi-agent systems.

Recommended citation: "Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems." EMNLP 2025. Role: fourth student author.