mlsanityData to 14 Oct 2026

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning

arXiv 2506.01710 ↗First posted 2 Jun 2025cs.CLcited by 18

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.

Key facts. Cited by 18 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 26 of its 57 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

26 of 57 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Table-R1: Inference-Time Scaling for Table Reasoning29 May
  2. 2025Table-R1: Region-based Reinforcement Learning for Table Understanding18 May
  3. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL29 Mar
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar

Other references · 22

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  5. 2024OpenAI o1 System Cardcited by 1,244
  6. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  8. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  9. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  10. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  11. 2025VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Taskscited by 285
  12. 2022Binding Language Models in Symbolic Languagescited by 228
10 more
  1. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
  2. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 167
  3. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 91
  4. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 77
  5. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 68
  6. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 68
  7. 2023TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPTcited by 59
  8. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 37
  9. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  10. 2023TableQAKit: A Comprehensive and Practical Toolkit for Table-based Question Answeringcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 10.

18 papers.

Sort:

By area:

  1. 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 50
  2. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
  3. 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 7
  4. 2026Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluationcited by 7
  5. 2025TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoningcited by 5
  6. 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Modelscited by 3
  7. 2026SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregationcited by 3
  8. 2026Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoningcited by 3
  9. 2026DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agentscited by 3
  10. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  11. 2026StrucTab: A Structured Optimization Framework for Table Parsingcited by 2
  12. 2025Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Taskcited by 1
6 more
  1. 2025CLARity: Reasoning Consistency Alone Can Teach Reinforced Expertscited by 1
  2. 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarioscited by 1
  3. 2026Probing How Scalable Table Data Enhances General Long-Context Reasoningcited by 1
  4. 2026Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QAcited by 0
  5. 2026Synthetic Contrastive Reasoning for Multi-Table Q&Acited by 0
  6. 2026Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
  2. 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
  3. 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models
  4. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning
  5. 2025Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
  6. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  7. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
  8. 2025TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning