mlsanityData to 14 Oct 2026

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning

arXiv 2607.02262 ↗First posted 2 Jul 2026cs.CLcited by 0

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

also in 1 more
Abstract (arXiv)

Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose CheckRLM, a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors. Specifically, CheckRLM extracts factual claims from the reasoning chain to identify and localize subtle knowledge inconsistencies during inference. Upon detection of errors, a refinement mechanism performs minimal-cost yet precise corrections by leveraging external knowledge, ensuring coherence between the reasoning chain and correct knowledge. Extensive experiments demonstrate that CheckRLM substantially outperforms existing baselines, exhibiting a strong capability to mitigate error accumulation in long-horizon reasoning with lower costs. The code and data are available at https://github.com/AI9Stars/CheckRLM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 52 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

11 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning4 Jun
  2. 2025Synergizing RAG and Reasoning: A Systematic Review22 Apr

Other references · 9

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  4. 2024Measuring short-form factuality in large language modelscited by 373
  5. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  6. 2025Are Reasoning Models More Prone to Hallucination?cited by 64
  7. 2025A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworkscited by 21
  8. 2025Supervising the search process produces reliable and generalizable information-seeking agentscited by 20
  9. 2025Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verificationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
  2. 2025From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
  3. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoning
  4. 2025ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
  5. 2024RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
  6. 2025You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
  7. 2025From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs
  8. 2026Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore