# ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement

arXiv: https://arxiv.org/abs/2504.20434 · HTML: https://mlsanity.com/paper/2504.20434/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 11 of 11)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse](https://mlsanity.com/paper/2410.21333/) (2024)
- [RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation](https://mlsanity.com/paper/2409.09584/) (2024)
- [An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities](https://mlsanity.com/paper/2501.13742/) (2025)
- [Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.19619/) (2024)
- [ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation](https://mlsanity.com/paper/2501.18460/) (2025)
- [Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.05159/) (2024)

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

- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [A Survey of Vibe Coding with Large Language Models](https://mlsanity.com/paper/2510.12399/) (2025)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages](https://mlsanity.com/paper/2603.09678/) (2026)
- [Large Language Models for Multilingual Code Intelligence: A Survey](https://mlsanity.com/paper/2604.25960/) (2026)
- [Performance Evaluation of General Purpose Large Language Models for Basic Linear Algebra Subprograms Code Generation](https://mlsanity.com/paper/2507.04697/) (2025)
- [MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning](https://mlsanity.com/paper/2606.11537/) (2026)
- [What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework](https://mlsanity.com/paper/2609.12746/) (2026)

## Abstract (arXiv)

We present Agentic Retrieval-Augmented Code Synthesis (ARCS), a system that improves LLM-based code generation without fine-tuning. ARCS operates through a budgeted synthesize-execute-repair loop over a frozen model: it retrieves relevant code context before generation, proposes candidates, executes them against tests, and repairs based on execution feedback. This retrieval-before-generation design reduces hallucination and accelerates convergence. We formalize ARCS as a state-action process with provable guarantees on termination, monotonic improvement, and bounded cost. A tiered controller (Small/Medium/Large) trades latency for accuracy predictably. On HumanEval, ARCS achieves up to 87.2% pass@1 with Llama-3.1-405B, surpassing CodeAgent (82.3%) while using simpler control than tree-search methods. On TransCoder, it achieves >= 90% accuracy on most translation pairs. On a LANL scientific corpus, it improves CodeBLEU by +0.115 over baseline RAG. ARCS provides a practical, reproducible approach to reliable code synthesis using existing LLM checkpoints.