# Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback

arXiv: https://arxiv.org/abs/2403.16792 · HTML: https://mlsanity.com/paper/2403.16792/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 58 references that are in the map.
- First posted on arXiv 25 Mar 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [Coder Reviewer Reranking for Code Generation](https://mlsanity.com/paper/2211.16490/) (2022)
- [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://mlsanity.com/paper/2212.10007/) (2022)
- [When Language Model Meets Private Library](https://mlsanity.com/paper/2210.17236/) (2022)
- [DevEval: Evaluating Code Generation in Practical Software Projects](https://mlsanity.com/paper/2401.06401/) (2024)
- [Learning to Generate Code Comments from Class Hierarchies](https://mlsanity.com/paper/2103.13426/) (2021)
- [Embedding API Dependency Graph for Neural Code Generation](https://mlsanity.com/paper/2103.15361/) (2021)

## Built on by (most cited first, 30 of 46)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation](https://mlsanity.com/paper/2409.09584/) (2024)
- [CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code](https://mlsanity.com/paper/2404.15639/) (2024)
- [The Future of AI-Driven Software Engineering](https://mlsanity.com/paper/2406.07737/) (2024)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond](https://mlsanity.com/paper/2503.20589/) (2025)
- [In Line with Context: Repository-Level Code Generation via Context Inlining](https://mlsanity.com/paper/2601.00376/) (2026)
- [Exploring the Potential of Diffusion Large Language Models in Code Generation](https://mlsanity.com/paper/2509.11252/) (2025)
- [How Far Are AI Scientists from Changing the World?](https://mlsanity.com/paper/2507.23276/) (2025)
- [Theorem Prover as a Judge for Synthetic Data Generation](https://mlsanity.com/paper/2502.13137/) (2025)
- [Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs](https://mlsanity.com/paper/2406.18294/) (2024)
- [AIR: Complex Instruction Generation via Automatic Iterative Refinement](https://mlsanity.com/paper/2502.17787/) (2025)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding](https://mlsanity.com/paper/2603.16124/) (2026)
- [CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale](https://mlsanity.com/paper/2502.16645/) (2025)
- [QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback](https://mlsanity.com/paper/2510.26101/) (2025)
- [C2: Scalable Auto-Feedback for LLM-based Chart Generation](https://mlsanity.com/paper/2410.18652/) (2024)
- [Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling](https://mlsanity.com/paper/2511.03404/) (2025)
- [Enhancing Project-Specific Code Completion by Inferring Internal API Information](https://mlsanity.com/paper/2507.20888/) (2025)
- [CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback](https://mlsanity.com/paper/2507.22080/) (2025)
- [VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations](https://mlsanity.com/paper/2503.19449/) (2025)
- [Prompt to Pwn: Automated Exploit Generation for Smart Contracts](https://mlsanity.com/paper/2508.01371/) (2025)
- [A Human-AI Collaborative Workflow for Mathematical Discovery: A Case Study in Grover-Compatible Riemannian Optimization](https://mlsanity.com/paper/2512.09443/) (2025)
- [Integrating Expert Knowledge into Logical Programs via LLMs](https://mlsanity.com/paper/2502.12275/) (2025)
- [CodeSSM: Towards State Space Models for Code Understanding](https://mlsanity.com/paper/2505.01475/) (2025)
- [Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation](https://mlsanity.com/paper/2509.00079/) (2025)
- [TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation](https://mlsanity.com/paper/2509.24148/) (2025)
- [textttReMind: Understanding Deductive Code Reasoning in LLMs](https://mlsanity.com/paper/2511.00488/) (2025)
- [RM -RF: Reward Model for Run-Free Unit Test Evaluation](https://mlsanity.com/paper/2601.13097/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project's context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate CoCoGen with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines.