Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911229962878976 |
|---|---|
| author | Zhou, Yuhang Zhang, Mingrui Li, Ke Wang, Mingyi Liu, Qiao Wang, Qifei Liu, Jiayi Liu, Fei Li, Serena Li, Weiwei Gao, Mingze Kumar, Abhishek Fan, Xiangjun Zhao, Zhuokai Zhang, Lizhu |
| author_facet | Zhou, Yuhang Zhang, Mingrui Li, Ke Wang, Mingyi Liu, Qiao Wang, Qifei Liu, Jiayi Liu, Fei Li, Serena Li, Weiwei Gao, Mingze Kumar, Abhishek Fan, Xiangjun Zhao, Zhuokai Zhang, Lizhu |
| contents | 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 OpenAI-o4-mini-high. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20176 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding Zhou, Yuhang Zhang, Mingrui Li, Ke Wang, Mingyi Liu, Qiao Wang, Qifei Liu, Jiayi Liu, Fei Li, Serena Li, Weiwei Gao, Mingze Kumar, Abhishek Fan, Xiangjun Zhao, Zhuokai Zhang, Lizhu Computation and Language Artificial Intelligence 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 OpenAI-o4-mini-high. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding. |
| title | Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.20176 |