Copertina

Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ouyang, Shuyin, Qian, Zhaozhi, AL-Tam, Faroq, AL-Qurishi, Muhammad, Zhang, Jie M.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Increasing the Thinking Budget is Not All You Need
di: Iacobacci, Ignacio, et al.
Pubblicazione: (2025)

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

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
di: Guo, Chengquan, et al.
Pubblicazione: (2024)

Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis
di: Dolcetti, Greta, et al.
Pubblicazione: (2024)

Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls
di: Fandina, Ora Nova, et al.
Pubblicazione: (2025)

Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements
di: Abtahi, Seyed Moein, et al.
Pubblicazione: (2025)

Beyond Autoregression: An Empirical Study of Diffusion Large Language Models for Code Generation
di: Li, Chengze, et al.
Pubblicazione: (2025)

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

Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs
di: Sakharova, Marina, et al.
Pubblicazione: (2025)

Combining Large Language Models with Static Analyzers for Code Review Generation
di: Jaoua, Imen, et al.
Pubblicazione: (2025)

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
di: Deshpande, Darshan, et al.
Pubblicazione: (2026)

Natural Emergent Misalignment from Reward Hacking in Production RL
di: MacDiarmid, Monte, et al.
Pubblicazione: (2025)

Toward Executable Repository-Level Code Generation via Environment Alignment
di: Pan, Ruwei, et al.
Pubblicazione: (2026)

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

Executing as You Generate: Hiding Execution Latency in LLM Code Generation
di: Sun, Zhensu, et al.
Pubblicazione: (2026)

CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks
di: Xie, Danning, et al.
Pubblicazione: (2025)

AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
di: Nunez, Ana, et al.
Pubblicazione: (2024)

An Empirical Study of the Non-determinism of ChatGPT in Code Generation
di: Ouyang, Shuyin, et al.
Pubblicazione: (2023)

Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling
di: Ni, Ziyi, et al.
Pubblicazione: (2024)

Unseen Horizons: Unveiling the Real Capability of LLM Code Generation Beyond the Familiar
di: Zhang, Yuanliang, et al.
Pubblicazione: (2024)

TENET: Leveraging Tests Beyond Validation for Code Generation
di: Hu, Yiran, et al.
Pubblicazione: (2025)

Static Program Analysis Guided LLM Based Unit Test Generation
di: Roychowdhury, Sujoy, et al.
Pubblicazione: (2025)

SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution
di: Lee, Woojin, et al.
Pubblicazione: (2026)

Learning Adaptive Parallel Execution for Efficient Code Localization
di: Xu, Ke, et al.
Pubblicazione: (2026)

One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks
di: Birillo, Anastasiia, et al.
Pubblicazione: (2024)

DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells
di: Cherief, Houcine Abdelkader, et al.
Pubblicazione: (2026)

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

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
di: Liu, Fang, et al.
Pubblicazione: (2024)

An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
di: Li, Yikun, et al.
Pubblicazione: (2026)

An AIC-based approach for articulating unpredictable problems in open complex environments
di: AL-Shareefy, Haider, et al.
Pubblicazione: (2024)

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
di: Liu, Aofan, et al.
Pubblicazione: (2025)

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

FasterPy: An LLM-based Code Execution Efficiency Optimization Framework
di: Wu, Yue, et al.
Pubblicazione: (2025)

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

BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
di: Li, Yuanhao, et al.
Pubblicazione: (2026)

Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
di: Jiang, Shan, et al.
Pubblicazione: (2026)

ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution
di: Wang, Yubang, et al.
Pubblicazione: (2026)

Tree-of-Code: A Hybrid Approach for Robust Complex Task Planning and Execution
di: Ni, Ziyi, et al.
Pubblicazione: (2024)

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
di: Petrovic, Nenad, et al.
Pubblicazione: (2025)

LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
di: Islam, Nafis Tanveer, et al.
Pubblicazione: (2024)