# CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2504.13534 · HTML: https://mlsanity.com/paper/2504.13534/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 95 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 9 of 9)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://mlsanity.com/paper/2308.13259/) (2023)
- [A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions](https://mlsanity.com/paper/2410.12837/) (2024)
- [CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model](https://mlsanity.com/paper/2311.05812/) (2023)
- [AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning](https://mlsanity.com/paper/2411.16495/) (2024)

## Built on by (most cited first, 8 of 8)

- [Step-GUI Technical Report](https://mlsanity.com/paper/2512.15431/) (2025)
- [Improving the Reliability of LLMs: Combining CoT, RAG, Self-Consistency, and Self-Verification](https://mlsanity.com/paper/2505.09031/) (2025)
- [A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding](https://mlsanity.com/paper/2505.21962/) (2025)
- [Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models](https://mlsanity.com/paper/2507.04023/) (2025)
- [RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systems](https://mlsanity.com/paper/2601.12991/) (2026)
- [ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.24388/) (2025)
- [Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning](https://mlsanity.com/paper/2604.14170/) (2026)
- [Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts](https://mlsanity.com/paper/2607.10411/) (2026)

## Abstract (arXiv)

Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance from natural language prompts compared with code prompts. To address these issues, we propose CoT-RAG, a novel reasoning framework with three key designs: (i) Knowledge Graph-driven CoT Generation, featuring knowledge graphs to modulate reasoning chain generation of LLMs, thereby enhancing reasoning credibility; (ii) Learnable Knowledge Case-aware RAG, which incorporates retrieval-augmented generation (RAG) into knowledge graphs to retrieve relevant sub-cases and sub-descriptions, providing LLMs with learnable information; (iii) Pseudo Program Prompting Execution, which promotes greater logical rigor by guiding LLMs to execute reasoning tasks as pseudo-programs. Evaluations on nine public datasets spanning three reasoning tasks reveal significant accuracy gains-ranging from 4.0% to 44.3%-over state-of-the-art methods. Furthermore, tests on four domain-specific datasets demonstrate exceptional accuracy and efficient execution, underscoring its practical applicability and scalability. Our code and data are available at https: //github.com/hustlfy123/CoT-RAG.