mlsanityData to 14 Oct 2026

Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning

arXiv 2508.17905 ↗First posted 25 Aug 2025cs.CLcited by 1

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

Abstract (arXiv)

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers between different SKR tasks, thereby constraining their overall performance in cross-task scenarios. In this paper, we introduce textscPandora, a novel USKR framework that addresses the limitations of existing methods by leveraging two key innovations. First, we propose a code-based unified knowledge representation using textscPython's textscPandas API, which aligns seamlessly with the pre-training of LLMs. This representation facilitates a cohesive approach to handling different structured knowledge sources. Building on this foundation, we employ knowledge transfer to bolster the unified reasoning process of LLMs by automatically building cross-task memory. By adaptively correcting reasoning using feedback from code execution, textscPandora showcases impressive unified reasoning capabilities. Extensive experiments on six widely used benchmarks across three SKR tasks demonstrate that textscPandora outperforms existing unified reasoning frameworks and competes effectively with task-specific methods.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 51 of its 68 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

51 of 68 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL2 Oct
  2. 2024Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments13 Mar
  3. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan

Other references · 48

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  10. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  11. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 515
  12. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
36 more
  1. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  2. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  3. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  4. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  7. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 235
  8. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  9. 2022Binding Language Models in Symbolic Languagescited by 228
  10. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  11. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  12. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
  13. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  14. 2020Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Basescited by 171
  15. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  16. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  17. 2017Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learningcited by 161
  18. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  19. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  20. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 84
  21. 2023Few-shot In-context Learning for Knowledge Base Question Answeringcited by 74
  22. 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
  23. 2022A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challengescited by 50
  24. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  25. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 36
  26. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  27. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  28. 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
  29. 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Searchcited by 22
  30. 2021Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphscited by 16
  31. 2023Code-Style In-Context Learning for Knowledge-Based Question Answeringcited by 13
  32. 2024TrustUQA: A Trustful Framework for Unified Structured Data Question Answeringcited by 12
  33. 2018Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answeringcited by 11
  34. 2024SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaborationcited by 11
  35. 2025Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generationcited by 8
  36. 2022Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Frameworkcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Modelscited by 18

Similar, not cited

Close in wording, no citation either way

  1. 2025Pandora: A Code-Driven Large Language Model Agent for Unified Reasoning Across Diverse Structured Knowledge
  2. 2025Last Layer Logits to Logic: Empowering LLMs with Logic-Consistent Structured Knowledge Reasoning
  3. 2024AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
  4. 2024An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration
  5. 2025Weaver: Interweaving SQL and LLM for Table Reasoning
  6. 2023DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
  7. 2026Co-Evolving Structured Knowledge and Reasoning in Language Models
  8. 2025OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases