# TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

arXiv: https://arxiv.org/abs/2509.06278 · HTML: https://mlsanity.com/paper/2509.06278/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 9 of 9)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [BERT: A Review of Applications in Natural Language Processing and Understanding](https://mlsanity.com/paper/2103.11943/) (2021)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT](https://mlsanity.com/paper/2307.08674/) (2023)
- [PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables](https://mlsanity.com/paper/2412.04272/) (2024)
- [Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables](https://mlsanity.com/paper/2506.11375/) (2025)

## Built on by (most cited first, 20 of 20)

- [Toward Efficient Agents: Memory, Tool learning, and Planning](https://mlsanity.com/paper/2601.14192/) (2026)
- [Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting](https://mlsanity.com/paper/2602.13802/) (2026)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities](https://mlsanity.com/paper/2604.18401/) (2026)
- [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)
- [PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization](https://mlsanity.com/paper/2601.10029/) (2026)
- [AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning](https://mlsanity.com/paper/2602.13807/) (2026)
- [Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing](https://mlsanity.com/paper/2603.06503/) (2026)
- [STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models](https://mlsanity.com/paper/2511.11233/) (2025)
- [From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation](https://mlsanity.com/paper/2512.03360/) (2025)
- [Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent](https://mlsanity.com/paper/2601.04879/) (2026)
- [TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Models](https://mlsanity.com/paper/2602.14089/) (2026)
- [Analyzing LLM Instruction Optimization for Tabular Fact Verification](https://mlsanity.com/paper/2602.17937/) (2026)
- [TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning](https://mlsanity.com/paper/2603.07528/) (2026)
- [TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning](https://mlsanity.com/paper/2606.10316/) (2026)
- [Contrastive Branch Policy Optimization](https://mlsanity.com/paper/2608.24300/) (2026)
- [GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning](https://mlsanity.com/paper/2603.02212/) (2026)
- [Towards Error-Free EHRs: Reasoning-Intensive Consistency Verification Between Clinical Notes and Structured Tables in Electronic Health Records](https://mlsanity.com/paper/2605.26463/) (2026)
- [MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning](https://mlsanity.com/paper/2606.11537/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a single-turn reasoning paradigm that processes flattened tables in a single forward pass. This paradigm suffers from inherent limitations, including context overflow on large tables, weak sensitivity to continuous numerical values, and the absence of explicit tool-use and reflection. In this paper, we propose TableMind, a tuning-based autonomous programmatic table agent that simulates the human-like cognitive schema of the multi-turn interaction within a lightweight LLM. Instead of adopting a training-free workflow design, TableMind learns to internalize planning, action, and reflection through a principled two-stage training strategy. To bootstrap structured table reasoning capabilities, we construct and filter high-quality reasoning data for the supervised fine-tuning (SFT) stage. To enable precise code generation, we introduce a designed multi-perspective reward scheme and a novel optimization objective in the reinforcement learning (RL) stage. Extensive experiments on diverse benchmarks demonstrate that TableMind consistently outperforms previous baselines, validating the effectiveness of training autonomous agents to improve overall performance.