# A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement

arXiv: https://arxiv.org/abs/2409.05001 · HTML: https://mlsanity.com/paper/2409.05001/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 8 Sep 2024.

## Builds on (most cited first, 30 of 33)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [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)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Multi-lingual Evaluation of Code Generation Models](https://mlsanity.com/paper/2210.14868/) (2022)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [Can Large Language Models Really Improve by Self-critiquing Their Own Plans?](https://mlsanity.com/paper/2310.08118/) (2023)
- [Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering](https://mlsanity.com/paper/2401.08500/) (2024)
- [Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming](https://mlsanity.com/paper/2302.07427/) (2023)
- [Batch Prompting: Efficient Inference with Large Language Model APIs](https://mlsanity.com/paper/2301.08721/) (2023)
- [Coder Reviewer Reranking for Code Generation](https://mlsanity.com/paper/2211.16490/) (2022)
- [Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning](https://mlsanity.com/paper/2304.11384/) (2023)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification](https://mlsanity.com/paper/2310.10996/) (2023)

## Built on by (most cited first, 21 of 21)

- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation](https://mlsanity.com/paper/2502.10802/) (2025)
- [LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities](https://mlsanity.com/paper/2601.09822/) (2026)
- [OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices](https://mlsanity.com/paper/2510.24145/) (2025)
- [Curiosity by Design: An LLM-based Coding Assistant Asking Clarification Questions](https://mlsanity.com/paper/2507.21285/) (2025)
- [Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation](https://mlsanity.com/paper/2510.10460/) (2025)
- [Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach](https://mlsanity.com/paper/2510.12120/) (2025)
- [Atomizer: An LLM-based Collaborative Multi-Agent Framework for Intent-Driven Commit Untangling](https://mlsanity.com/paper/2601.01233/) (2026)
- [Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback](https://mlsanity.com/paper/2506.18315/) (2025)
- [Agentic Framework for Epidemiological Modeling](https://mlsanity.com/paper/2602.00299/) (2026)
- [To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing](https://mlsanity.com/paper/2604.27296/) (2026)
- [CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels](https://mlsanity.com/paper/2605.05023/) (2026)
- [PaT: Planning-after-Trial for Efficient Test-Time Code Generation](https://mlsanity.com/paper/2605.07248/) (2026)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems](https://mlsanity.com/paper/2602.02138/) (2026)
- [Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks](https://mlsanity.com/paper/2602.06976/) (2026)
- [Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus](https://mlsanity.com/paper/2603.29292/) (2026)
- [Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation](https://mlsanity.com/paper/2510.19868/) (2025)
- [From Helpful to Trustworthy: LLM Agents for Pair Programming](https://mlsanity.com/paper/2604.10300/) (2026)
- [CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation](https://mlsanity.com/paper/2604.13946/) (2026)
- [MARS: Multi-Specialist LLM Relay System for Competitive Programming](https://mlsanity.com/paper/2608.23918/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved impressive performance on code generation. Although prior studies enhanced LLMs with prompting techniques and code refinement, they still struggle with complex programming problems due to rigid solution plans. In this paper, we draw on pair programming practices to propose PairCoder, a novel LLM-based framework for code generation. PairCoder incorporates two collaborative LLM agents, namely a Navigator agent for high-level planning and a Driver agent for specific implementation. The Navigator is responsible for proposing promising solution plans, selecting the current optimal plan, and directing the next iteration round based on execution feedback. The Driver follows the guidance of Navigator to undertake initial code generation, code testing, and refinement. This interleaved and iterative workflow involves multi-plan exploration and feedback-based refinement, which mimics the collaboration of pair programmers. We evaluate PairCoder with both open-source and closed-source LLMs on various code generation benchmarks. Extensive experimental results demonstrate the superior accuracy of PairCoder, achieving relative pass@1 improvements of 12.00%-162.43% compared to prompting LLMs directly.