# IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues

arXiv: https://arxiv.org/abs/2405.13021 · HTML: https://mlsanity.com/paper/2405.13021/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 15 May 2024.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control](https://mlsanity.com/paper/1611.02796/) (2016)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community](https://mlsanity.com/paper/2307.09751/) (2023)
- [Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue](https://mlsanity.com/paper/2311.07445/) (2023)
- [Tackling Vision Language Tasks Through Learning Inner Monologues](https://mlsanity.com/paper/2308.09970/) (2023)

## Built on by (most cited first, 30 of 40)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models](https://mlsanity.com/paper/2410.03577/) (2024)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals](https://mlsanity.com/paper/2502.16101/) (2025)
- [Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers](https://mlsanity.com/paper/2506.00054/) (2025)
- [Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing](https://mlsanity.com/paper/2505.02811/) (2025)
- [Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2501.18845/) (2025)
- [LettinGo: Explore User Profile Generation for Recommendation System](https://mlsanity.com/paper/2506.18309/) (2025)
- [Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models](https://mlsanity.com/paper/2505.03075/) (2025)
- [Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.16237/) (2025)
- [KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing](https://mlsanity.com/paper/2505.20245/) (2025)
- [Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering](https://mlsanity.com/paper/2501.07813/) (2025)
- [Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech Synthesis](https://mlsanity.com/paper/2501.06467/) (2025)
- [Research on the Online Update Method for Retrieval-Augmented Generation (RAG) Model with Incremental Learning](https://mlsanity.com/paper/2501.07063/) (2025)
- [Towards Transparent RAG: Fostering Evidence Traceability in LLM Generation via Reinforcement Learning](https://mlsanity.com/paper/2505.13258/) (2025)
- [RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering](https://mlsanity.com/paper/2506.16988/) (2025)
- [Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training](https://mlsanity.com/paper/2511.07328/) (2025)
- [Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning](https://mlsanity.com/paper/2505.17086/) (2025)
- [Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory](https://mlsanity.com/paper/2605.24602/) (2026)
- [MedAI: Evaluating TxAgent's Therapeutic Agentic Reasoning in the NeurIPS CURE-Bench Competition](https://mlsanity.com/paper/2512.11682/) (2025)
- [Incorporating Q&A Nuggets into Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.13222/) (2026)
- [DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering](https://mlsanity.com/paper/2601.16478/) (2026)
- [Retrieval-Augmented Robots via Retrieve-Reason-Act](https://mlsanity.com/paper/2603.02688/) (2026)
- [A Survey of Query Optimization in Large Language Models](https://mlsanity.com/paper/2412.17558/) (2024)
- [GenIR: Generative Visual Feedback for Mental Image Retrieval](https://mlsanity.com/paper/2506.06220/) (2025)
- [From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades](https://mlsanity.com/paper/2509.22984/) (2025)
- [SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.15682/) (2025)
- [When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering](https://mlsanity.com/paper/2601.19827/) (2026)
- [Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling](https://mlsanity.com/paper/2602.21317/) (2026)
- [Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage](https://mlsanity.com/paper/2603.08819/) (2026)

## Abstract (arXiv)

Although the Retrieval-Augmented Generation (RAG) paradigms can use external knowledge to enhance and ground the outputs of Large Language Models (LLMs) to mitigate generative hallucinations and static knowledge base problems, they still suffer from limited flexibility in adopting Information Retrieval (IR) systems with varying capabilities, constrained interpretability during the multi-round retrieval process, and a lack of end-to-end optimization. To address these challenges, we propose a novel LLM-centric approach, IM-RAG, that integrates IR systems with LLMs to support multi-round RAG through learning Inner Monologues (IM, i.e., the human inner voice that narrates one's thoughts). During the IM process, the LLM serves as the core reasoning model (i.e., Reasoner) to either propose queries to collect more information via the Retriever or to provide a final answer based on the conversational context. We also introduce a Refiner that improves the outputs from the Retriever, effectively bridging the gap between the Reasoner and IR modules with varying capabilities and fostering multi-round communications. The entire IM process is optimized via Reinforcement Learning (RL) where a Progress Tracker is incorporated to provide mid-step rewards, and the answer prediction is further separately optimized via Supervised Fine-Tuning (SFT). We conduct extensive experiments with the HotPotQA dataset, a popular benchmark for retrieval-based, multi-step question-answering. The results show that our approach achieves state-of-the-art (SOTA) performance while providing high flexibility in integrating IR modules as well as strong interpretability exhibited in the learned inner monologues.