mlsanityData to 7 Oct 2026

Table-R1: Region-based Reinforcement Learning for Table Understanding

arXiv 2505.12415 ↗First posted 18 May 2025cs.CL cs.AIcited by 35

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

Abstract (arXiv)

Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for effective comprehension. While large language models (LLMs) have demonstrated potential in table reasoning through prompting and techniques like chain-of-thought (CoT) and program-of-thought (PoT), optimizing their performance for table question answering remains underexplored. In this paper, we introduce region-based Table-R1, a novel reinforcement learning approach that enhances LLM table understanding by integrating region evidence into reasoning steps. Our method employs Region-Enhanced Supervised Fine-Tuning (RE-SFT) to guide models in identifying relevant table regions before generating answers, incorporating textual, symbolic, and program-based reasoning. Additionally, Table-Aware Group Relative Policy Optimization (TARPO) introduces a mixed reward system to dynamically balance region accuracy and answer correctness, with decaying region rewards and consistency penalties to align reasoning steps. Experiments show that Table-R1 achieves an average performance improvement of 14.36 points across multiple base models on three benchmark datasets, even outperforming baseline models with ten times the parameters, while TARPO reduces response token consumption by 67.5% compared to GRPO, significantly advancing LLM capabilities in efficient tabular reasoning.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 38 of its 71 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

38 of 71 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition15 Apr
  2. 2024ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context4 Mar
  3. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  4. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan

Other references · 34

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Qwen Technical Reportcited by 3,273
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  8. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  9. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  10. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  11. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  12. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
22 more
  1. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  2. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  3. 2022Binding Language Models in Symbolic Languagescited by 224
  4. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  5. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  6. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  7. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  8. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  9. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
  10. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  11. 2023LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzlescited by 41
  12. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  13. 2022HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Datacited by 28
  14. 2019Answering Conversational Questions on Structured Data without Logical Formscited by 24
  15. 2024When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Modelscited by 22
  16. 2024Evaluating and Aligning CodeLLMs on Human Preferencecited by 22
  17. 2023Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characterscited by 21
  18. 2024ExecRepoBench: Multi-level Executable Code Completion Evaluationcited by 19
  19. 2025Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generationcited by 9
  20. 2025LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimizationcited by 9
  21. 2023cTBLS: Augmenting Large Language Models with Conversational Tablescited by 7
  22. 2025Multi-Agent Collaboration for Multilingual Code Instruction Tuningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 16; 2026: 19.

35 papers.

Sort:

By area:

  1. 2025Rethinking Entropy Interventions in RLVR: An Entropy Change Perspectivecited by 50
  2. 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoningcited by 18
  3. 2025Scaling Generalist Data-Analytic Agentscited by 11
  4. 2025When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tablescited by 10
  5. 2026Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Searchcited by 8
  6. 2026Reinforced Efficient Reasoning via Semantically Diverse Explorationcited by 8
  7. 2026ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratchcited by 8
  8. 2026FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Modelscited by 8
  9. 2025MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extractioncited by 6
  10. 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 6
  11. 2026One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinementcited by 6
  12. 2025T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tablescited by 5
23 more
  1. 2025TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoningcited by 5
  2. 2025Emotional Support with LLM-based Empathetic Dialogue Generationcited by 4
  3. 2025M3TQA: Massively Multilingual Multitask Table Question Answeringcited by 3
  4. 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
  5. 2025Same Content, Different Representations: A Controlled Study for Table QAcited by 3
  6. 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Modelscited by 3
  7. 2026TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answeringcited by 3
  8. 2025Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligencecited by 2
  9. 2026Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoningcited by 2
  10. 2025MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedbackcited by 1
  11. 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarioscited by 1
  12. 2026Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancementcited by 1
  13. 2026Probing How Scalable Table Data Enhances General Long-Context Reasoningcited by 1
  14. 2026TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesiscited by 1
  15. 2026When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errorscited by 1
  16. 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Modelscited by 0
  17. 2026Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QAcited by 0
  18. 2026A Closer Look into LLMs for Table Understandingcited by 0
  19. 2026V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimizationcited by 0
  20. 2026Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspectivecited by 0
  21. 2026CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verificationcited by 0
  22. 2026VeriGraph: Towards Verifiable Data-Analytic Agentscited by 0
  23. 2026BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewardscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TableGPT-R1: Advancing Tabular Reasoning Through Reinforcement Learning
  2. 2025Can GRPO Boost Complex Multimodal Table Understanding?
  3. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning
  4. 2025OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
  5. 2025Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
  6. 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
  7. 2025Table-R1: Inference-Time Scaling for Table Reasoning
  8. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards