AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

How Far Can LLM Agents Reason with Tables? Benchmarking Multi-Turn Agentic Table Question Answering in the Wild

Jingwang Huang, Jie Zhang, Haoyang Zeng, Changzai Pan, Xianjie Wu, Guanting Dong, Jiaheng Liu, Wei Zhang, Mingyu Zheng, Chunxiao Liu, Kaiwen Wei, Jiang Zhong and 1 more

ICML 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces TableAgent-Bench, a benchmark for evaluating LLM agents on multi-turn, tool-using table question answering in realistic settings.

Problem

Existing TableQA benchmarks treat the task as passive, single-turn understanding and cannot evaluate autonomous reasoning and tool-call trajectories in multi-turn scenarios.

Approach

A large-scale benchmark that frames TableQA as multi-turn agentic interaction, evaluating reasoning and tool-call trajectories rather than only single-turn answers.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enable thinking modeKimi-K2 · TableAgent-Benchinformation coverage: +12.1% IC over non-thinkingImproved
enable thinking modeClaude-Haiku-4-5 · TableAgent-Benchinformation coverage: 41.00 -> 51.10Improved
enable thinking modeDeepSeek-V3.2 · TableAgent-Benchinformation coverage: 27.50 -> 46.80Improved
enable thinking modeQwen3-8B · TableAgent-Benchinformation coverage: 2.80 -> 2.75No clear effect
add exact-matching and semantic-retrieval tools to code execution (ablation)Claude-Haiku-4-5 · toolset ablationinformation coverage: 46.20 -> 53.40Improved
add exact-matching and semantic-retrieval tools to code execution (ablation)DeepSeek-V3.2 · toolset ablationtable relevance recall: 65.1 -> 78.2Improved
add exact-matching tool to code execution (ablation)DeepSeek-V3.2 · toolset ablationinformation coverage: 43.0 -> 41.50Hurt
add table processing tools to CE+EM+SR (ablation)DeepSeek-V3.2 · toolset ablationinformation coverage: 44.90 -> 46.80Improved
add table processing tools to CE+EM+SR (ablation)Mimo-V2-Flash · toolset ablationinformation coverage: 45.00 -> 45.60Improved
add table processing tools to CE+EM+SR (ablation)Claude-Haiku-4-5 · toolset ablationinformation coverage: 53.40 -> 51.10Hurt
increase interaction steps at fixed 128k context, or context length at fixed 70 steps (ablation)table agents · context/step analysisperformanceImproved
higher table recall and precisiontable agents · TableAgent-Benchinformation coverageImproved

Experimental setup

Benchmarks: TableAgent-Bench

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy