# Process Supervision-Guided Policy Optimization for Code Generation

arXiv: https://arxiv.org/abs/2410.17621 · HTML: https://mlsanity.com/paper/2410.17621/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X](https://mlsanity.com/paper/2303.17568/) (2023)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms](https://mlsanity.com/paper/2406.02900/) (2024)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [Execution-based Code Generation using Deep Reinforcement Learning](https://mlsanity.com/paper/2301.13816/) (2023)
- [StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback](https://mlsanity.com/paper/2402.01391/) (2024)
- [Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision](https://mlsanity.com/paper/2402.02658/) (2024)
- [Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing](https://mlsanity.com/paper/2402.00658/) (2024)

## Built on by (most cited first, 26 of 26)

- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future](https://mlsanity.com/paper/2504.12328/) (2025)
- [Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators](https://mlsanity.com/paper/2504.15253/) (2025)
- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [Process-Supervised Reinforcement Learning for Code Generation](https://mlsanity.com/paper/2502.01715/) (2025)
- [Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation](https://mlsanity.com/paper/2412.15118/) (2024)
- [Teaching Your Models to Understand Code via Focal Preference Alignment](https://mlsanity.com/paper/2503.02783/) (2025)
- [Improving LLM-Generated Code Quality with GRPO](https://mlsanity.com/paper/2506.02211/) (2025)
- [PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization](https://mlsanity.com/paper/2601.07182/) (2026)
- [Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning](https://mlsanity.com/paper/2604.07941/) (2026)
- [OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation](https://mlsanity.com/paper/2501.13264/) (2025)
- [Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation](https://mlsanity.com/paper/2601.03525/) (2026)
- [CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generation](https://mlsanity.com/paper/2505.10594/) (2025)
- [RM -RF: Reward Model for Run-Free Unit Test Evaluation](https://mlsanity.com/paper/2601.13097/) (2026)
- [When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems](https://mlsanity.com/paper/2602.08272/) (2026)
- [From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding](https://mlsanity.com/paper/2605.15951/) (2026)
- [Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL](https://mlsanity.com/paper/2605.28751/) (2026)
- [X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests](https://mlsanity.com/paper/2601.06953/) (2026)
- [DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation](https://mlsanity.com/paper/2601.22230/) (2026)
- [Rethinking Agentic Reinforcement Learning In Large Language Models](https://mlsanity.com/paper/2604.27859/) (2026)
- [PRO-CUA: Process-Reward Optimization for Computer Use Agents](https://mlsanity.com/paper/2605.29119/) (2026)
- [Process Rewards with Learned Reliability](https://mlsanity.com/paper/2605.15529/) (2026)
- [EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling](https://mlsanity.com/paper/2606.26578/) (2026)
- [DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning](https://mlsanity.com/paper/2607.26457/) (2026)
- [Function-Level Execution Feedback for Code Preference Optimization](https://mlsanity.com/paper/2608.23632/) (2026)
- [Performance Foundations of Parallel & Distributed Reasoning Language Models](https://mlsanity.com/paper/2608.27046/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental improvements. When generated code fails all unit tests, no learning signal is received, hindering progress on complex tasks. To address this, we propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement and providing immediate guidance. We explore various strategies for training PRMs and integrating them into the RL framework, finding that using PRMs both as dense rewards and for value function initialization significantly boosts performance. Our experimental results also highlight the effectiveness of PRMs in enhancing RL-driven code generation, especially for long-horizon scenarios.