Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thought reasoning and question decomposition, lack error detection mechanisms and discard problem-solving experiences, contrasting sharply with how humans tackle such problems. In this paper, we propose MAPLE (Multi-agent Adaptive Planning with Long-term mEmory), a novel framework that mimics human problem-solving through specialized cognitive agents working in a feedback-driven loop. MAPLE integrates 4 key components: (1) a Solver using the ReAct paradigm for reasoning, (2) a Checker for answer verification, (3) a Reflector for error diagnosis and strategy correction, and (4) an Archiver managing long-term memory for experience reuse and evolution. Experiments on WiKiTQ and TabFact demonstrate significant improvements over existing methods, achieving state-of-the-art performance across multiple LLM backbones.

翻译：基于表格的问答任务需要复杂的推理能力，而当前大型语言模型通过单次推理难以实现这一目标。现有方法（如思维链推理和问题分解）缺乏错误检测机制，且丢弃了问题解决经验，这与人类处理此类问题的方式形成鲜明对比。本文提出MAPLE（基于长期记忆的多智能体自适应规划框架），这是一种通过专业认知智能体在反馈驱动循环中协作、模拟人类问题解决过程的新颖框架。MAPLE整合了四个关键组件：（1）采用ReAct范式进行推理的求解器，（2）用于答案验证的检查器，（3）进行错误诊断与策略修正的反思器，以及（4）管理长期记忆以实现经验复用与演化的归档器。在WiKiTQ和TabFact数据集上的实验表明，该方法相比现有技术取得显著提升，并在多种大型语言模型基座上实现了最先进的性能。