Saved in:
Bibliographic Details
Main Authors: Bai, Ye, Wang, Minghan, Vu, Thuy-Trang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05813
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914159455633408
author Bai, Ye
Wang, Minghan
Vu, Thuy-Trang
author_facet Bai, Ye
Wang, Minghan
Vu, Thuy-Trang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05813
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
Bai, Ye
Wang, Minghan
Vu, Thuy-Trang
Computation and Language
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.
title MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
topic Computation and Language
url https://arxiv.org/abs/2506.05813