Cover Image

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hao, Li, Rui, Sha, Lei, Zhang, Jie M.
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
by: Tian, Yuchen, et al.
Published: (2024)

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
by: Jiang, Xue, et al.
Published: (2025)

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
by: Dou, Shihan, et al.
Published: (2024)

Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey
by: Wang, Junqiao, et al.
Published: (2024)

NExT: Teaching Large Language Models to Reason about Code Execution
by: Ni, Ansong, et al.
Published: (2024)

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories
by: Li, Jia, et al.
Published: (2024)

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
by: Fan, Lishui, et al.
Published: (2025)

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
by: Yu, Zhuohao, et al.
Published: (2024)

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
by: Zheng, Tianyu, et al.
Published: (2024)

CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
by: Xie, Yiqing, et al.
Published: (2024)

ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
by: Tang, Lingxiao, et al.
Published: (2026)

EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories
by: Li, Jia, et al.
Published: (2024)

GenX: Mastering Code and Test Generation with Execution Feedback
by: Wang, Nan, et al.
Published: (2024)

PurpCode: Reasoning for Safer Code Generation
by: Liu, Jiawei, et al.
Published: (2025)

Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
by: Zhao, Songwen, et al.
Published: (2025)

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
by: Yang, Dayu, et al.
Published: (2025)

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

CodeMind: Evaluating Large Language Models for Code Reasoning
by: Liu, Changshu, et al.
Published: (2024)

Evaluating and Achieving Controllable Code Completion in Code LLM
by: Zhang, Jiajun, et al.
Published: (2026)

SelfCodeAlign: Self-Alignment for Code Generation
by: Wei, Yuxiang, et al.
Published: (2024)

CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
by: Wang, Sizhe, et al.
Published: (2025)

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
by: Zhuo, Terry Yue, et al.
Published: (2025)

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora
by: Li, Shangyu, et al.
Published: (2026)

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
by: Fu, Lingyue, et al.
Published: (2025)

CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning
by: Tang, Lingxiao, et al.
Published: (2025)

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
by: Sutawika, Lintang, et al.
Published: (2026)

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
by: Zhu, Mingzhi, et al.
Published: (2026)

Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulation
by: Abdollahi, Mohammad, et al.
Published: (2025)

Pragmatic Reasoning improves LLM Code Generation
by: Cao, Zhuchen, et al.
Published: (2025)

Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation
by: Pysklo, Hubert M., et al.
Published: (2026)

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
by: Yan, Weixiang, et al.
Published: (2023)

Python Symbolic Execution with LLM-powered Code Generation
by: Wang, Wenhan, et al.
Published: (2024)

SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis
by: Li, Yansong, et al.
Published: (2025)

DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
by: Han, Hojae, et al.
Published: (2026)

EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
by: Huang, Dong, et al.
Published: (2024)

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
by: Wang, Zhengren, et al.
Published: (2025)

LLMSniffer: Detecting LLM-Generated Code via GraphCodeBERT and Supervised Contrastive Learning
by: Dihan, Mahir Labib, et al.
Published: (2026)

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

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
by: Wang, Zimu, et al.
Published: (2026)

Model Editing for LLMs4Code: How Far are We?
by: Li, Xiaopeng, et al.
Published: (2024)