mlsanityData to 7 Oct 2026

MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning

arXiv 2506.05813 ↗First posted 6 Jun 2025cs.CLcited by 4

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 46 of its 56 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

46 of 56 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning17 Feb
  2. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation2 Oct

Other references · 44

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2024Qwen2.5 Technical Reportcited by 4,713
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  11. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  12. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
32 more
  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  2. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  3. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  4. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  5. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  6. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  7. 2023Cognitive Architectures for Language Agentscited by 422
  8. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  9. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  10. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  11. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 231
  12. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  13. 2022Binding Language Models in Symbolic Languagescited by 224
  14. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  15. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  16. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 171
  17. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Gamecited by 148
  18. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 143
  19. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  20. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  21. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  22. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  23. 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
  24. 2023RET-LLM: Towards a General Read-Write Memory for Large Language Modelscited by 64
  25. 2023Collaborating with language models for embodied reasoningcited by 61
  26. 2023Multi-Agent Consensus Seeking via Large Language Modelscited by 50
  27. 2023AvalonBench: Evaluating LLMs Playing the Game of Avaloncited by 45
  28. 2022PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingcited by 41
  29. 2023AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisationcited by 31
  30. 2023Simulating Public Administration Crisis: A Novel Generative Agent-Based Simulation System to Lower Technology Barriers in Social Science Researchcited by 21
  31. 2023LLM As DBAcited by 18
  32. 2023Co-NavGPT: Multi-Robot Cooperative Visual Semantic Navigation Using Vision Language Modelscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  2. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  4. 2026SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
  2. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
  3. 2025Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
  4. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  5. 2025Mission Impossible: Feedback-Guided Dynamic Interactive Planning for Improving Reasoning on LLMs
  6. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  7. 2025Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects
  8. 2026Adaptive Latent Agentic Reasoning