mlsanityData to 7 Oct 2026

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

arXiv 2604.10734 ↗First posted 12 Apr 2026cs.CLcited by 5

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent hallucinations. To address these issues, we propose Self-Correcting RAG, a unified framework that reformulates retrieval and generation as constrained optimization and path planning. On the input side, we move beyond traditional greedy retrieval and, for the first time, formalize context selection as a multi-dimensional multiple-choice knapsack problem (MMKP), thereby maximizing information density and removing redundancy under a strict token budget. On the output side, we introduce a natural language inference (NLI)-guided Monte Carlo Tree Search (MCTS) mechanism, which leverages test-time compute to dynamically explore reasoning trajectories and validate the faithfulness of generated answers. Experiments on six multi-hop question answering and fact-checking datasets demonstrate that our method significantly improves reasoning accuracy on complex queries while effectively reducing hallucinations, outperforming strong existing baselines.Our code is available at https://github.com/xjiacs/Self-Correcting-RAG .

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 50 of its 84 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

50 of 84 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Adaptive Stopping for Multi-Turn LLM Reasoning1 Apr

Other references · 49

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  11. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  12. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
37 more
  1. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  2. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  4. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  5. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  7. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  8. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  10. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  11. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  12. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  13. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  14. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  15. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  16. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  17. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  18. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  19. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  20. 2023Large Language Model Guided Tree-of-Thoughtcited by 218
  21. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  22. 2023REST: Retrieval-Based Speculative Decodingcited by 148
  23. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  24. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 29
  25. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 20
  26. 2025Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoningcited by 17
  27. 2026FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answeringcited by 16
  28. 2025EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corporacited by 14
  29. 2025CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstentioncited by 10
  30. 2025Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGcited by 8
  31. 2025Revealing Perception and Generation Dynamics in LVLMs: Mitigating Hallucinations via Validated Dominance Correctioncited by 6
  32. 2025Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answeringcited by 5
  33. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  34. 2026NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answeringcited by 3
  35. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  36. 2024Self-Evolution Fine-Tuning for Policy Optimizationcited by 2
  37. 2026NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spacescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Retrieval as Generation: A Unified Framework with Self-Triggered Information Planningcited by 5
  2. 2026Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMscited by 3
  3. 2026When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapsecited by 1
  4. 2026Customer-Agent: Overcoming Context Limitations in Ultra-Long Shopping Trajectories via Tool-Augmented Agents and RLVRcited by 0
  5. 2026Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applicationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
  2. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  3. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
  4. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answering
  5. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  6. 2025Multi-hop Reasoning via Early Knowledge Alignment
  7. 2025RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering
  8. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures