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

TL;DR

This paper introduces Mixture-of-Minds, a multi-agent reinforcement learning framework that improves table understanding by decomposing reasoning into specialized roles and using code execution for precise manipulation.

Contribution

It presents a novel multi-agent approach with planning, coding, and answering roles, combined with self-improvement via reinforcement learning, to enhance table reasoning accuracy.

Findings

Achieves 62.13% on TableBench, outperforming previous models.

Demonstrates the effectiveness of multi-agent decomposition for table reasoning.

Shows significant improvements over baseline methods.

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.