# A Multi-Agent Approach for Claim Verification from Tabular Data Documents

arXiv: https://arxiv.org/abs/2604.17225 · HTML: https://mlsanity.com/paper/2604.17225/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 18 of 18)

- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables](https://mlsanity.com/paper/2305.13186/) (2023)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [TableRAG: Million-Token Table Understanding with Language Models](https://mlsanity.com/paper/2410.04739/) (2024)
- [SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)](https://mlsanity.com/paper/2105.13995/) (2021)
- [OpenTab: Advancing Large Language Models as Open-domain Table Reasoners](https://mlsanity.com/paper/2402.14361/) (2024)
- [ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context](https://mlsanity.com/paper/2403.02177/) (2024)
- [TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2401.13223/) (2024)
- [FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents](https://mlsanity.com/paper/2411.05764/) (2024)
- [GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering](https://mlsanity.com/paper/2412.01230/) (2024)
- [TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training](https://mlsanity.com/paper/2104.01099/) (2021)
- [TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning](https://mlsanity.com/paper/2409.11724/) (2024)
- [Volta at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables using TAPAS and Transfer Learning](https://mlsanity.com/paper/2106.00248/) (2021)

## Abstract (arXiv)

We present a novel approach for claim verification from tabular data documents. Recent LLM-based approaches either employ complex pretraining/fine-tuning or decompose verification into subtasks, often lacking comprehensive explanations and generalizability. To address these limitations, we propose a Multi-Agentic framework for Claim verification (MACE) consisting of three specialized agents: Planner, Executor, and Verifier. Instead of elaborate finetuning, each agent employs a zero-shot Chain-of-Thought setup to perform its tasks. MACE produces interpretable verification traces, with the Planner generating explicit reasoning strategies, the Executor providing detailed computation steps, and the Verifier validating the logic. Experiments demonstrate that MACE achieves state-of-the-art (SOTA) performance on two datasets and performs on par with the best models on two others, while achieving 80--100% of best performance with substantially smaller models: 27--92B parameters versus 235B. This combination of competitive performance, memory efficiency, and transparent reasoning highlights our framework's effectiveness.