Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding

• URL: http://arxiv.org/abs/2510.20176v2
• Date: Fri, 24 Oct 2025 15:36:31 GMT
• Title: Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
• Authors: Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei Li, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang,
• Abstract summary: We propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering.<n>We show that Mixture-of-Minds delivers substantial gains, reaching 62.13% on TableBench and surpassing OpenAI-o4-mini-high.
• Score: 32.583090212983805
• License: http://creativecommons.org/licenses/by/4.0/
• 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 OpenAI-o4-mini-high. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding.

Related papers

• JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models [58.408398005993455]
  JT-DA-8B is a specialized large language model designed for complex table reasoning tasks across diverse real-world scenarios.<n>We construct a comprehensive and diverse training corpus with 34 well-defined table reasoning tasks, by aggregating 29 public table QA datasets and 3 million tables.<n> Experimental results show that JT-DA-8B achieves strong performance in various table reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-07T14:29:23Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding [52.59372043981724]
  TableDART is a training-efficient framework that integrates multimodal views by reusing pretrained single-modality models.<n>In addition, we propose a novel agent to cross-modal knowledge integration by analyzing outputs from text- and image-based models.
  arXiv  Detail & Related papers  (2025-09-18T07:00:13Z)
• TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning [10.267950603662776]
  TableMind is a tool-integrated table reasoning agent that autonomously performs multi-turn tool invocation, writes and executes code in a secure sandbox environment for data analysis and precise numerical reasoning.<n>To realize these capabilities, we adopt a two-stage fine-tuning paradigm built on top of a powerful pre-trained language model.
  arXiv  Detail & Related papers  (2025-09-08T02:00:31Z)
• TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering [26.00027389659854]
  TableZoomer is a programming-based agent framework for the table question answering (TQA) task.<n>It introduces three key innovations: (1) replacing the original fully verbalized table with structured table schema to bridge the semantic gap and reduce computational complexity; (2) a query-aware table zooming mechanism that dynamically generates sub-table schema through column selection and entity linking; and (3) a Program-of-Thoughts (PoT) strategy that transforms queries into executable code to mitigate numerical hallucination.
  arXiv  Detail & Related papers  (2025-09-01T09:53:01Z)
• TalentMine: LLM-Based Extraction and Question-Answering from Multimodal Talent Tables [5.365164774382722]
  We introduce TalentMine, a novel framework that transforms extracted tables into semantically enriched representations.<n> TalentMine achieves 100% accuracy in query answering tasks compared to 0% for standard AWS Textract extraction.<n>Our comparative analysis also reveals that the Claude v3 Haiku model achieves optimal performance for talent management applications.
  arXiv  Detail & Related papers  (2025-06-22T22:17:42Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications [0.9831489366502302]
  This work introduces MATATA, a novel weakly supervised end-to-end approach to train multi-step reasoning language agents.<n>MATATA presents an annotation-free paradigm for each agent to enhance 3.8B/8B SLMs.<n>Experiments demonstrate that MATATA achieves state-of-the-art on FinQA, and on TAT-QA among reasoning methods based on open-source SLMs.
  arXiv  Detail & Related papers  (2024-11-28T05:12:17Z)
• TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning [61.14586098005874]
  Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning.<n>We introduce our Tool-Augmented Reasoning framework for Tables (TART), which integrates LLMs with specialized tools.<n>TART contains three key components: a table formatter to ensure accurate data representation, a tool maker to develop specific computational tools, and an explanation generator to maintain explainability.
  arXiv  Detail & Related papers  (2024-09-18T06:19:59Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.