mlsanityData to 14 Oct 2026

Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experience

arXiv 2506.00842 ↗First posted 1 Jun 2025cs.CL cs.AIcited by 8

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

also in 1 more
Abstract (arXiv)

Large language models (LLMs) achieve strong performance on plain text tasks but underperform on structured data like tables and databases. Potential challenges arise from their underexposure during pre-training and rigid text-to-structure transfer mechanisms. Unlike humans who seamlessly apply learned patterns across data modalities, LLMs struggle to infer implicit relationships embedded in tabular formats, especially in the absence of explicit structural guidance. To bridge this cognitive gap, we introduce Contrastive Retrieval-Augmented Generation on Experience (CoRE), a framework that builds experience memory representations and enhances generalization through contrastive In-Context Learning (ICL) to simulate human-like knowledge transfer. Experiments on Text-to-SQL and TableQA show CoRE significantly improves performance, achieving average gains of 3.44% and 4.24%, with up to 17.2% on challenging tasks. Our Monte Carlo Tree Search (MCTS)-generated Experience Memory expands training data 8-9x, enhancing diversity and domain coverage. This training-free and continual method propels LLMs toward structured knowledge expertise.

Key facts. Cited by 8 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 51 references that are in the map. First posted on arXiv 1 Jun 2025.

Builds on

26 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan

Other references · 24

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Let's Verify Step by Stepcited by 3,789
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2024A Survey on LLM-as-a-Judgecited by 1,423
  6. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  7. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  9. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  11. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  12. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 222
12 more
  1. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 208
  2. 2024Corrective Retrieval Augmented Generationcited by 197
  3. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
  4. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  5. 2023Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generationcited by 74
  6. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  7. 2023Contrastive Chain-of-Thought Promptingcited by 52
  8. 2024ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understandingcited by 46
  9. 2023SAIL: Search-Augmented Instruction Learningcited by 33
  10. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  11. 2023OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilitiescited by 10
  12. 2024Grimoire is All You Need for Enhancing Large Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agentcited by 119
  2. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 5
  3. 2025HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Storescited by 3
  4. 2026GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Tracescited by 3
  5. 2026A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvementcited by 0
  6. 2026Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAGcited by 0
  7. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Modelscited by 0
  8. 2026Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
  2. 2026CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval
  3. 2025RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
  4. 2025Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning
  5. 2026To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval
  6. 2026Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
  7. 2025RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
  8. 2024Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations