Image de couverture de livre

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Zhuohao, Gu, Weizheng, Wang, Yidong, Jiang, Xingru, Zeng, Zhengran, Wang, Jindong, Ye, Wei, Zhang, Shikun
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence Machine Learning Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CodeShell Technical Report
par: Xie, Rui, et autres
Publié: (2024)

CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
par: Zeng, Zhengran, et autres
Publié: (2024)

Benchmarking and Studying the LLM-based Code Review
par: Zeng, Zhengran, et autres
Publié: (2025)

A Survey on Evaluating Large Language Models in Code Generation Tasks
par: Chen, Liguo, et autres
Publié: (2024)

ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation
par: Xu, Yijiang, et autres
Publié: (2024)

An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
par: Xing, Chengli, et autres
Publié: (2026)

Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development
par: Zeng, Zhengran, et autres
Publié: (2025)

Seed&Steer: Guiding Large Language Models with Compilable Prefix and Branch Signals for Unit Test Generation
par: Zhou, Shuaiyu, et autres
Publié: (2025)

ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
par: Tang, Lingxiao, et autres
Publié: (2026)

CodeScore: Evaluating Code Generation by Learning Code Execution
par: Dong, Yihong, et autres
Publié: (2023)

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
par: Fan, Lishui, et autres
Publié: (2025)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
par: Yu, Zhuohao, et autres
Publié: (2025)

Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation
par: Abdollahi, Mohammad, et autres
Publié: (2025)

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
par: Gu, Alex, et autres
Publié: (2024)

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning
par: Wang, Hao, et autres
Publié: (2026)

Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation
par: Ouyang, Shuyin, et autres
Publié: (2026)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
par: Guo, Chengquan, et autres
Publié: (2024)

Learning Adaptive Parallel Execution for Efficient Code Localization
par: Xu, Ke, et autres
Publié: (2026)

GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
par: Liu, Zhuoyao, et autres
Publié: (2026)

Assessing Coherency and Consistency of Code Execution Reasoning by Large Language Models
par: Liu, Changshu, et autres
Publié: (2025)

A Study on Thinking Patterns of Large Reasoning Models in Code Generation
par: Halim, Kevin, et autres
Publié: (2025)

Inducing Vulnerable Code Generation in LLM Coding Assistants
par: Zeng, Binqi, et autres
Publié: (2025)

Process-Supervised Reinforcement Learning for Code Generation
par: Ye, Yufan, et autres
Publié: (2025)

SecCodePRM: A Process Reward Model for Code Security
par: Yu, Weichen, et autres
Publié: (2026)

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
par: Li, Yikun, et autres
Publié: (2026)

An approach for performance requirements verification and test environments generation
par: Abdeen, Waleed, et autres
Publié: (2024)

A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models
par: Liu, Changshu, et autres
Publié: (2025)

FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation
par: Zhang, Ruiyi, et autres
Publié: (2026)

RewardAnything: Generalizable Principle-Following Reward Models
par: Yu, Zhuohao, et autres
Publié: (2025)

CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
par: Tang, Lingxiao, et autres
Publié: (2025)

Python Symbolic Execution with LLM-powered Code Generation
par: Wang, Wenhan, et autres
Publié: (2024)

GenX: Mastering Code and Test Generation with Execution Feedback
par: Wang, Nan, et autres
Publié: (2024)

Integrating Symbolic Execution with LLMs for Automated Generation of Program Specifications
par: Yang, Fanpeng, et autres
Publié: (2025)

From UI to Code: Mobile Ads Detection via LLM-Unified Static-Dynamic Analysis
par: Ma, Shang, et autres
Publié: (2026)

Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
par: Li, Yanlong, et autres
Publié: (2025)

SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
par: Han, Hao, et autres
Publié: (2026)

CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
par: Chen, Zaoyu, et autres
Publié: (2026)

Compiling Code LLMs into Lightweight Executables
par: Shi, Jieke, et autres
Publié: (2026)

SelfPiCo: Self-Guided Partial Code Execution with LLMs
par: Xue, Zhipeng, et autres
Publié: (2024)

Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates
par: Sun, Zhihong, et autres
Publié: (2024)