DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
On the map: LLM reasoning → Reinforcement learning for reasoning
Abstract (arXiv)
Process Reward Models (PRMs) have become essential for improving Large Language Models (LLMs) via test-time scaling, yet their effectiveness in coding remains limited due to the lack of meaningful step decompositions in code and the noise of Monte-Carlo-generated partial labels. We propose DreamPRM-Code, a coding-focused PRM that treats functions as reasoning steps using a Chain-of-Function prompting strategy to induce modular code generation, enabling PRM training and application analogous to mathematical reasoning tasks. To address label noise, DreamPRM-Code introduces a meta-learning-based correction mechanism that leverages clean final-solution unit-test labels and performs bi-level optimization to refine intermediate labels. Applying on test-time scaling, DreamPRM-Code achieved state-of-the-art performance on LiveCodeBench with 80.9 pass@1 rate, surpassing OpenAI o4-mini.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 5 of its 24 references that are in the map. First posted on arXiv 17 Dec 2025.
Builds on
5 of 24 references.
Closest ancestors · 1
Same direction, newest first
Other references · 4
- 2025Qwen3 Technical Reportcited by 8,820
- 2024Qwen2.5 Technical Reportcited by 4,942
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
- 2024OpenAI o1 System Cardcited by 1,244
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learningcited by 1
- 2026VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Toolscited by 1
- 2026The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignmentcited by 0
- 2026The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment26 Jun 2026
- 2026VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools17 Jun 2026
- 2026QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning20 Apr 2026
Similar, not cited
Close in wording, no citation either way
- 2026FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation
- 2023Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
- 2025From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
- 2025GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
- 2025FreePRM: Training Process Reward Models Without Ground Truth Process Labels
- 2025Efficient Process Reward Model Training via Active Learning
- 2025Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards
- 2025R-PRM: Reasoning-Driven Process Reward Modeling