# Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models

arXiv: https://arxiv.org/abs/2506.08352 · HTML: https://mlsanity.com/paper/2506.08352/

## Key facts

- Cited by 3 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 31 of its 38 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines](https://mlsanity.com/paper/2409.12959/) (2024)
- [MindSearch: Mimicking Human Minds Elicits Deep AI Searcher](https://mlsanity.com/paper/2407.20183/) (2024)
- [When Search Engine Services meet Large Language Models: Visions and Challenges](https://mlsanity.com/paper/2407.00128/) (2024)
- [FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models](https://mlsanity.com/paper/2401.10744/) (2024)
- [Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Engines](https://mlsanity.com/paper/2402.19421/) (2024)
- [An Agent Framework for Real-Time Financial Information Searching with Large Language Models](https://mlsanity.com/paper/2502.15684/) (2024)
- [Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents](https://mlsanity.com/paper/2505.12065/) (2025)

## Built on by (most cited first, 3 of 3)

- [Reinforcement Learning Foundations for Deep Research Systems: A Survey](https://mlsanity.com/paper/2509.06733/) (2025)
- [Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study](https://mlsanity.com/paper/2507.04043/) (2025)
- [Constructing and Interpreting Digital Twin Representations for Visual Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2511.12365/) (2025)

## Abstract (arXiv)

Large language models (LLMs) can face factual limitations when responding to time-sensitive queries about recent events that arise after their knowledge thresholds in the training corpus. Existing search-augmented approaches fall into two categories, each with distinct limitations: multi-agent search frameworks incur substantial computational overhead by separating search planning and response synthesis across multiple LLMs, while single-LLM tool-calling methods restrict themselves to sequential planned, single-query searches from sole search sources. We present Reasoning-Search (R-Search), a single-LLM search framework that unifies multi-step planning, multi-source search execution, and answer synthesis within one coherent inference process. Innovatively, it structure the output into four explicitly defined components, including reasoning steps that guide the search process (<think>), a natural-language directed acyclic graph that represents the search plans with respect to diverse sources (<search>), retrieved results from executing the search plans (<result>), and synthesized final answers (<answer>). To enable effective generation of these structured outputs, we propose a specialized Reinforcement Fine-Tuning (ReFT) method based on GRPO, together with a multi-component reward function that optimizes LLM's answer correctness, structural validity of the generated DAG, and adherence to the defined output format. Experimental evaluation on FinSearchBench-24, SearchExpertBench-25, and seven Q and A benchmarks demonstrates that R-Search outperforms state-of-the-art methods, while achieving substantial efficiency gains through 70% reduction in context token usage and approximately 50% decrease in execution latency. Code is available at https://github.com/wentao0429/Reasoning-search.