# CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents

arXiv: https://arxiv.org/abs/2603.17829 · HTML: https://mlsanity.com/paper/2603.17829/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 62 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [CodeSearchNet Challenge: Evaluating the State of Semantic Code Search](https://mlsanity.com/paper/1909.09436/) (2019)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning](https://mlsanity.com/paper/2505.24298/) (2025)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [OrcaLoca: An LLM Agent Framework for Software Issue Localization](https://mlsanity.com/paper/2502.00350/) (2025)
- [Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning](https://mlsanity.com/paper/2306.03350/) (2023)
- [SWE-QA: Can Language Models Answer Repository-level Code Questions?](https://mlsanity.com/paper/2509.14635/) (2025)
- [Coding Agents with Multimodal Browsing are Generalist Problem Solvers](https://mlsanity.com/paper/2506.03011/) (2025)
- [Tool-integrated Reinforcement Learning for Repo Deep Search](https://mlsanity.com/paper/2508.03012/) (2025)
- [CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance](https://mlsanity.com/paper/2507.10646/) (2025)

## Built on by (most cited first, 9 of 9)

- [Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction](https://mlsanity.com/paper/2605.05242/) (2026)
- [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [FastContext: Training Efficient Repository Explorer for Coding Agents](https://mlsanity.com/paper/2606.14066/) (2026)
- [LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents](https://mlsanity.com/paper/2608.17393/) (2026)
- [Antares: Foundation Models for Agentic Vulnerability Localization](https://mlsanity.com/paper/2608.02407/) (2026)
- [Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale](https://mlsanity.com/paper/2609.15939/) (2026)
- [Semantic Navigation for Issue Localization in Code Repository](https://mlsanity.com/paper/2609.31176/) (2026)
- [Small Agents with Semantic Search: Efficient Multilingual Code Localization](https://mlsanity.com/paper/2610.05099/) (2026)

## Abstract (arXiv)

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using embedding-based retrieval approaches such as vector search, recent work has focused on developing agents to localize relevant code either as a standalone precursor to or interleaved with performing actual work. Most prior methods on agentic code search equip the agent with complex, specialized tools, such as repository graphs derived from static analysis. In this paper, we demonstrate that, with an effective reinforcement learning recipe, a coding agent equipped with nothing more than a standard Unix terminal can be trained to achieve strong results. Our experiments on three benchmarks (SWE-Bench Verified, Pro, and Lite) reveal that our models consistently achieve superior or competitive performance over 2-18x larger base and post-trained LLMs and sometimes approach performance provided by closed models like Claude Sonnet, even when using specialized scaffolds. Our work particularly focuses on techniques for re-purposing existing coding agent environments for code search, reward design, and RL optimization. We release the resulting model family, CodeScout, along with all our code and data for the community to build upon.