Imagen de Portada

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhu, Xiao, Zhou, Xinyu, Zhu, Boyu, Hu, Hanxu, Du, Mingzhe, Zhang, Haotian, Wang, Huiming, Guo, Zhijiang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient RLVR Training via Weighted Mutual Information Data Selection
por: Zhou, Xinyu, et al.
Publicado: (2026)

CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
por: Chen, Zaoyu, et al.
Publicado: (2026)

CHARM: Calibrating Reward Models With Chatbot Arena Scores
por: Zhu, Xiao, et al.
Publicado: (2025)

From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling
por: Chen, Zhengyu, et al.
Publicado: (2025)

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
por: Qing, Yuhao, et al.
Publicado: (2025)

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
por: Song, Xiaoshuai, et al.
Publicado: (2026)

On the Power of (Approximate) Reward Models for Inference-Time Scaling
por: Zhu, Youheng, et al.
Publicado: (2026)

Dynamic Scaling of Unit Tests for Code Reward Modeling
por: Ma, Zeyao, et al.
Publicado: (2025)

Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
por: Wu, Tianyi, et al.
Publicado: (2026)

Atom of Thoughts for Markov LLM Test-Time Scaling
por: Teng, Fengwei, et al.
Publicado: (2025)

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
por: Wang, Aozhe, et al.
Publicado: (2026)

Measuring the Influence of Incorrect Code on Test Generation
por: Huang, Dong, et al.
Publicado: (2024)

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
por: Yang, Zhicheng, et al.
Publicado: (2025)

Scaling Test-Time Compute for Agentic Coding
por: Kim, Joongwon, et al.
Publicado: (2026)

DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
por: Hu, Hanxu, et al.
Publicado: (2026)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
por: Hu, Junze, et al.
Publicado: (2025)

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation
por: Wang, Yutong, et al.
Publicado: (2025)

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
por: Ke, Changxin, et al.
Publicado: (2026)

CodeChemist: Functional Knowledge Transfer for Low-Resource Code Generation via Test-Time Scaling
por: Wang, Kaixin, et al.
Publicado: (2025)

S*: Test Time Scaling for Code Generation
por: Li, Dacheng, et al.
Publicado: (2025)

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
por: Liu, Zihan, et al.
Publicado: (2025)

Mercury: A Code Efficiency Benchmark for Code Large Language Models
por: Du, Mingzhe, et al.
Publicado: (2024)

CodeArena: A Collective Evaluation Platform for LLM Code Generation
por: Du, Mingzhe, et al.
Publicado: (2025)

Additive Conjucyclic Codes over $\F_{q^2}$: Trace Correspondence and Applications to Quantum Codes
por: Lv, Jingjie, et al.
Publicado: (2020)

DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation
por: Qin, Peijia, et al.
Publicado: (2026)

Entropy Centroids as Intrinsic Rewards for Test-Time Scaling
por: Zhao, Wenshuo, et al.
Publicado: (2026)

Code Generation by Differential Test Time Scaling
por: He, Yifeng, et al.
Publicado: (2026)

Inference-Time Scaling for Generalist Reward Modeling
por: Liu, Zijun, et al.
Publicado: (2025)

Prior Constraints-based Reward Model Training for Aligning Large Language Models
por: Zhou, Hang, et al.
Publicado: (2024)

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
por: Wang, Haozhe, et al.
Publicado: (2026)

PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations
por: Guo, Chengcheng, et al.
Publicado: (2026)

Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
por: Fu, Jia, et al.
Publicado: (2025)

SecCodePRM: A Process Reward Model for Code Security
por: Yu, Weichen, et al.
Publicado: (2026)

Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
por: Karlekar, Sweta, et al.
Publicado: (2026)

Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
por: Yao, Yuxuan, et al.
Publicado: (2024)

DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
por: Zhang, Ruiyi, et al.
Publicado: (2025)

Eureka: Human-Level Reward Design via Coding Large Language Models
por: Ma, Yecheng Jason, et al.
Publicado: (2023)

OptScaler: A Collaborative Framework for Robust Autoscaling in the Cloud
por: Zou, Ding, et al.
Publicado: (2023)

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation
por: Dai, Yihan, et al.
Publicado: (2025)

GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
por: Zhao, Jian, et al.
Publicado: (2025)