Copertina

Beyond pass@k: Redundancy-Aware RLVR for Multi-Sample Code Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Florian, Le Bronnec, Verine, Alexandre, Yokota, Rio, Negrevergne, Benjamin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Precision and Recall to assess the quality and diversity of LLMs
di: Bronnec, Florian Le, et al.
Pubblicazione: (2024)

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
di: Zheng, Jiasheng, et al.
Pubblicazione: (2026)

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
di: Verine, Alexandre, et al.
Pubblicazione: (2025)

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
di: Zheng, Jiasheng, et al.
Pubblicazione: (2024)

Environment-Aware Code Generation: How far are We?
di: Wu, Tongtong, et al.
Pubblicazione: (2026)

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

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
di: Chen, Guoxin, et al.
Pubblicazione: (2026)

EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
di: Huang, Dong, et al.
Pubblicazione: (2024)

Evaluation of Code LLMs on Geospatial Code Generation
di: Gramacki, Piotr, et al.
Pubblicazione: (2024)

Show and Tell: Prompt Strategies for Style Control in Multi-Turn LLM Code Generation
di: Bohr, Jeremiah
Pubblicazione: (2025)

Code Fingerprints: Disentangled Attribution of LLM-Generated Code
di: Guo, Jiaxun, et al.
Pubblicazione: (2026)

VersiCode: Towards Version-controllable Code Generation
di: Wu, Tongtong, et al.
Pubblicazione: (2024)

CodeRAG-Bench: Can Retrieval Augment Code Generation?
di: Wang, Zora Zhiruo, et al.
Pubblicazione: (2024)

Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval
di: Wang, Jiexin, et al.
Pubblicazione: (2024)

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

AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators
di: Chou, Jason, et al.
Pubblicazione: (2025)

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
di: Li, Jia, et al.
Pubblicazione: (2024)

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

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
di: Gong, Linyuan, et al.
Pubblicazione: (2024)

DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal
di: Aggarwal, Vaibhav, et al.
Pubblicazione: (2025)

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

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
di: Bi, Zhangqian, et al.
Pubblicazione: (2024)

NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation
di: Saadi, Hossain Shaikh, et al.
Pubblicazione: (2025)

CYCLE: Learning to Self-Refine the Code Generation
di: Ding, Yangruibo, et al.
Pubblicazione: (2024)

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

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

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
di: Cheng, Wei, et al.
Pubblicazione: (2026)

CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation
di: Doan, Duy Tung, et al.
Pubblicazione: (2026)

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

EffiBench: Benchmarking the Efficiency of Automatically Generated Code
di: Huang, Dong, et al.
Pubblicazione: (2024)

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning
di: Zhang, Jiajun, et al.
Pubblicazione: (2026)

Enhancing Project-Specific Code Completion by Inferring Internal API Information
di: Deng, Le, et al.
Pubblicazione: (2025)

From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation
di: Bui, Minh Duc, et al.
Pubblicazione: (2026)

Measuring LLM Code Generation Stability via Structural Entropy
di: Song, Yewei, et al.
Pubblicazione: (2025)

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

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

FairCoder: Evaluating Social Bias of LLMs in Code Generation
di: Du, Yongkang, et al.
Pubblicazione: (2025)

Showing LLM-Generated Code Selectively Based on Confidence of LLMs
di: Li, Jia, et al.
Pubblicazione: (2024)

From Output to Evaluation: Does Raw Instruction-Tuned Code LLMs Output Suffice for Fill-in-the-Middle Code Generation?
di: Ahmad, Wasi Uddin, et al.
Pubblicazione: (2025)

Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge
di: Mu, Wenhan, et al.
Pubblicazione: (2025)