@inproceedings{zhu-etal-2025-bridging,
    title = "Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing {LLM}-based Multi-Agent Systems",
    author = "Zhu, Minghang  and
      Shi, Zhengliang  and
      Xu, Zhiwei  and
      Wu, Shiguang  and
      Wang, Lingjie  and
      Ren, Pengjie  and
      Ren, Zhaochun  and
      Chen, Zhumin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.1192/",
    doi = "10.18653/v1/2025.findings-emnlp.1192",
    pages = "21846--21861",
    ISBN = "979-8-89176-335-7",
    abstract = "The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a grounding agent for executing tool-use actions. Most existing methods typically fine-tune these agents independently, leading to capability gaps among them with poor coordination. To address this, we propose MOAT, a Multi-Agent Joint Alignment Tuning framework that improves agents collaboration through iterative alignment. MOAT alternates between two key stages: (1) Planning Agent Alignment, which optimizes the planning agent to generate subgoal sequences that better guide the grounding agent; and (2) Grounding Agent Improving, which fine-tunes the grounding agent using diverse subgoal-action pairs generated by the agent itself to enhance its generalization capablity. Theoretical analysis proves that MOAT ensures a non-decreasing and progressively convergent training process. Experiments across six benchmarks demonstrate that MOAT outperforms state-of-the-art baselines, achieving average improvements of 3.1{\%} on held-in tasks and 4.4{\%} on held-out tasks."
}