# s3: You Don't Need That Much Data to Train a Search Agent via RL

arXiv: https://arxiv.org/abs/2505.14146 · HTML: https://mlsanity.com/paper/2505.14146/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains](https://mlsanity.com/paper/2503.23829/) (2025)
- [A Replication Study of Dense Passage Retriever](https://mlsanity.com/paper/2104.05740/) (2021)
- [SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction](https://mlsanity.com/paper/2503.01478/) (2025)
- [Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation](https://mlsanity.com/paper/2406.14979/) (2024)

## Built on by (most cited first, 30 of 42)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [Dr. Zero: Self-Evolving Search Agents without Training Data](https://mlsanity.com/paper/2601.07055/) (2026)
- [MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework](https://mlsanity.com/paper/2508.14880/) (2025)
- [A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications](https://mlsanity.com/paper/2510.16724/) (2025)
- [DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2507.17365/) (2025)
- [Reinforcement Learning Foundations for Deep Research Systems: A Survey](https://mlsanity.com/paper/2509.06733/) (2025)
- [ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards](https://mlsanity.com/paper/2510.00568/) (2025)
- [The Interplay of Harness Design and Post-Training in LLM Agents](https://mlsanity.com/paper/2606.25447/) (2026)
- [AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2508.20368/) (2025)
- [QAgent: A modular Search Agent with Interactive Query Understanding](https://mlsanity.com/paper/2510.08383/) (2025)
- [AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction](https://mlsanity.com/paper/2510.15339/) (2025)
- [TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework](https://mlsanity.com/paper/2511.05385/) (2025)
- [Uncertainty Quantification for Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2510.11483/) (2025)
- [JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG](https://mlsanity.com/paper/2601.21916/) (2026)
- [Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents](https://mlsanity.com/paper/2510.04695/) (2025)
- [Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics](https://mlsanity.com/paper/2510.05137/) (2025)
- [Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering](https://mlsanity.com/paper/2509.00798/) (2025)
- [M3Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning](https://mlsanity.com/paper/2601.09278/) (2026)
- [BranPO: Scalable Contrastive Branch Sampling for Long-Horizon Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.03719/) (2026)
- [MultiCube-RAG for Multi-hop Question Answering](https://mlsanity.com/paper/2602.15898/) (2026)
- [ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents](https://mlsanity.com/paper/2606.03239/) (2026)
- [Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?](https://mlsanity.com/paper/2607.17558/) (2026)
- [Structure-Augmented Reasoning Generation](https://mlsanity.com/paper/2506.08364/) (2025)
- [Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities](https://mlsanity.com/paper/2601.21937/) (2026)
- [LensVLM: Selective Context Expansion for Compressed Visual Representation of Text](https://mlsanity.com/paper/2605.07019/) (2026)
- [SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search](https://mlsanity.com/paper/2605.29796/) (2026)
- [Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals](https://mlsanity.com/paper/2606.10684/) (2026)
- [It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning](https://mlsanity.com/paper/2609.00638/) (2026)
- [Multi-hop Reasoning via Early Knowledge Alignment](https://mlsanity.com/paper/2512.20144/) (2025)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference. Recent advances have enabled LLMs to act as search agents via reinforcement learning (RL), improving information acquisition through multi-turn interactions with retrieval engines. However, existing approaches either optimize retrieval using search-only metrics (e.g., NDCG) that ignore downstream utility or fine-tune the entire LLM to jointly reason and retrieve-entangling retrieval with generation and limiting the real search utility and compatibility with frozen or proprietary models. In this work, we propose s3, a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the searcher using a Gain Beyond RAG reward: the improvement in generation accuracy over naive RAG. s3 requires only 2.4k training samples to outperform baselines trained on over 70x more data, consistently delivering stronger downstream performance across six general QA and five medical QA benchmarks.