# Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning

arXiv: https://arxiv.org/abs/2502.11799 · HTML: https://mlsanity.com/paper/2502.11799/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs](https://mlsanity.com/paper/2412.19513/) (2024)
- [Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic](https://mlsanity.com/paper/2408.16326/) (2024)

## Built on by (most cited first, 30 of 32)

- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Table-R1: Inference-Time Scaling for Table Reasoning](https://mlsanity.com/paper/2505.23621/) (2025)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2602.19843/) (2026)
- [AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent](https://mlsanity.com/paper/2602.03955/) (2026)
- [MEraser: An Effective Fingerprint Erasure Approach for Large Language Models](https://mlsanity.com/paper/2506.12551/) (2025)
- [Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning](https://mlsanity.com/paper/2509.21193/) (2025)
- [RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals](https://mlsanity.com/paper/2505.15110/) (2025)
- [When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables](https://mlsanity.com/paper/2509.17680/) (2025)
- [Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning](https://mlsanity.com/paper/2505.00016/) (2025)
- [Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search](https://mlsanity.com/paper/2601.03851/) (2026)
- [Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models](https://mlsanity.com/paper/2506.06137/) (2025)
- [PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy](https://mlsanity.com/paper/2505.20429/) (2025)
- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning](https://mlsanity.com/paper/2506.05813/) (2025)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition](https://mlsanity.com/paper/2607.13347/) (2026)
- [Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents](https://mlsanity.com/paper/2609.11677/) (2026)
- [Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS](https://mlsanity.com/paper/2503.10674/) (2025)
- [CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments](https://mlsanity.com/paper/2606.06399/) (2026)
- [The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation](https://mlsanity.com/paper/2606.03032/) (2026)
- [MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems](https://mlsanity.com/paper/2510.01523/) (2025)
- [JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models](https://mlsanity.com/paper/2512.06859/) (2025)
- [DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework](https://mlsanity.com/paper/2602.00996/) (2026)
- [DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering](https://mlsanity.com/paper/2603.09152/) (2026)
- [FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning](https://mlsanity.com/paper/2603.12702/) (2026)
- [UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning](https://mlsanity.com/paper/2604.05517/) (2026)
- [Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering](https://mlsanity.com/paper/2607.22633/) (2026)
- [TabScope: Question-Adaptive Scope Selection for Table Question Answering](https://mlsanity.com/paper/2609.03395/) (2026)

## Abstract (arXiv)

Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning processes. While existing approaches have explored various decomposition strategies, they often lack effective mechanisms to identify and correct errors in intermediate reasoning steps, leading to cascading error propagation. To address these issues, we propose Table-Critic, a novel multi-agent framework that facilitates collaborative criticism and iterative refinement of the reasoning process until convergence to correct solutions. Our framework consists of four specialized agents: a Judge for error identification, a Critic for comprehensive critiques, a Refiner for process improvement, and a Curator for pattern distillation. To effectively deal with diverse and unpredictable error types, we introduce a self-evolving template tree that systematically accumulates critique knowledge through experience-driven learning and guides future reflections. Extensive experiments have demonstrated that Table-Critic achieves substantial improvements over existing methods, achieving superior accuracy and error correction rates while maintaining computational efficiency and lower solution degradation rate.