@inproceedings{zhou-etal-2026-mixture,
    title = "Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding",
    author = "Zhou, Yuhang  and
      Zhang, Mingrui  and
      Li, Ke  and
      Wang, Mingyi  and
      Liu, Qiao  and
      Wang, Qifei  and
      Liu, Jiayi  and
      Liu, Fei  and
      Li, Serena  and
      LI, Weiwei  and
      Gao, Mingze  and
      Kumar, Abhishek  and
      Fan, Xiangjun  and
      Zhao, Zhuokai  and
      Zhang, Lizhu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.112/",
    pages = "2424--2439",
    ISBN = "979-8-89176-390-6",
    abstract = "Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approaches remain limited. Fine-tuning based methods strengthen language reasoning; yet they are prone to arithmetic errors and hallucination. In contrast, tool-based methods enable precise table manipulation but rely on rigid schemas and lack semantic understanding. These complementary drawbacks highlight the need for approaches that integrate robust reasoning with reliable table processing. In this work, we propose MIXTURE-OF-MINDS, a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. This design enables each agent to focus on a specific aspect of the task while leveraging code execution for precise table manipulation. Building on this workflow, we introduce a self-improvement training framework that employs Monte Carlo Tree Search (MCTS) rollouts to generate pseudo-gold trajectories and optimize agents with reinforcement learning (RL). Extensive experiments show that MIXTURE-OF-MINDS delivers substantial gains, reaching 62.13{\%} on TableBench and surpassing GPT-o3-mini. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding."
}