MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringTable-based Question AnsweringSimilar Papers 제목 키워드 기반
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing clo…
Reinforcement LearningAutonomous DrivingMAPLE: A Mobile Assistant with Persistent Finite State Machines for Recovery Reasoning
Mobile GUI agents aim to autonomously complete user-instructed tasks across mobile apps. Recent advances in Multimodal Large Language Models (MLLMs) enable these agents to interpret UI screens, identify actionable elemen…
MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems
Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectur…
IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learning
This paper studies how to improve the generalization performance and learning speed of the navigation agents trained with deep reinforcement learning (DRL). Although DRL exhibits huge potential in robot mapless navigatio…
Deep Reinforcement LearningReinforcement Learning (RL)Maplets: An Efficient Approach for Cooperative SLAM Map Building Under Communication and Computation Constraints
This article introduces an approach to facilitate cooperative exploration and mapping of large-scale, near-ground, underground, or indoor spaces via a novel integration framework for locally-dense agent map data. The eff…
Simultaneous Localization and Mapping