paper-with-me

Papers

DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding

2025-12-17 · Ruiyi Zhang, Peijia Qin, Qi Cao, Pengtao Xie 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.

📄 PDF Abstract BibTeX arXiv:2512.15000

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ReasoningCode Generation

Results from the Paper

RankTaskDatasetModelMetrics
#26 Code Generation LiveCodeBench DreamPRM-Code Pass@1: 80.9

Similar Papers 제목 키워드 기반

DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning

2025-05-26 · Qi Cao, Ruiyi Wang, Ruiyi Zhang, Sai Ashish Somayajula 외

Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) offer a fine-grained evaluation of interme…

Meta-LearningMultimodal Reasoning

DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training

2025-09-05 · Qi Cao, Pengtao Xie arxiv

Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., Drea…

Multimodal Reasoning

FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation

2026-01-29 · Ruiyi Zhang, Peijia Qin, Qi Cao, Eric Xue 외 arxiv

Code generation is a core application of large language models (LLMs), yet LLMs still frequently fail on complex programming tasks. Given its success in mathematical reasoning, test-time scaling approaches such as Proces…

Mathematical ReasoningCode Generation

StepPRM-RTL: Stepwise Process-Reward Guided LLM Fine-Tuning for Enhanced RTL Synthesis

2026-06-02 · Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi, Ehsan Degan 외 arxiv

Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict correctness constraints in Verilog and VHDL. We present StepPRM-RTL, a …

Trajectory ModelingCode Generation

Automated Rewards via LLM-Generated Progress Functions

2024-10-11 · Vishnu Sarukkai, Brennan Shacklett, Zander Majercik, Kush Bhatia 외

Large Language Models (LLMs) have the potential to automate reward engineering by leveraging their broad domain knowledge across various tasks. However, they often need many iterations of trial-and-error to generate effe…