paper-with-me

홈 › Papers

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

2026-05-27 · Le Bronnec Florian, Alexandre Verine, Rio Yokota, Benjamin Negrevergne arxiv

LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit tests under a finite sampling budget. While recent verifier-based reinforcement learning (RLVR) methods improve executable correctness, how these objectives affect redundancy among sampled programs remains poorly understood. In this work, we study implementation-level redundancy in code generation using JPlag, a plagiarism-detection system for code. Across models and benchmarks, we show that correctness-only RLVR often concentrates generations around repeated implementations, whereas Pass@k-aware objectives maintain lower redundancy and improve larger-budget performance. Motivated by these observations, we augment RLVR with direct anti-redundancy rewards based on JPlag similarity. Across 3 models and 3 benchmarks, discouraging near-duplicate generations reliably improves finite-budget executable performance, often matching or outperforming specialized Pass@k-aware objectives.

📄 PDF Abstract BibTeX arXiv:2605.28022

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningCode Generation

Similar Papers 제목 키워드 기반

Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model

2026-06-21 · Pengxiang Cai, Tianchen Fang, Xiaohan Li, Qingyuan Zeng 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent works, however, suggest that mainstream RLVR often reallocates sampli…

Reinforcement Learning

The Multiple Ticket Hypothesis: Random Sparse Subnetworks Suffice for RLVR

2026-02-02 · Israel Adewuyi, Solomon Okibe, Vladmir Ivanov arxiv

The Lottery Ticket Hypothesis demonstrated that sparse subnetworks can match full-model performance, suggesting parameter redundancy. Meanwhile, in Reinforcement Learning with Verifiable Rewards (RLVR), recent work has s…

Reinforcement Learning

Understanding Diversity Collapse in RLVR via the Lens of Overtraining

2026-06-13 · Suqin Yuan, Jinkun Chen, Jiyang Zheng, Muyang Li 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from \emph{diversity collapse}: Pass@$1$ improve…

Reinforcement Learning

Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning

2026-03-03 · Anas Zafar, Leema Krishna Murali, Ashish Vashist arxiv

Recent work shows that text-only reinforcement learning with verifiable rewards (RLVR) can match or outperform image-text RLVR on multimodal medical VQA benchmarks, suggesting current evaluation protocols may fail to mea…

Reinforcement LearningVisual ReasoningVisual Grounding

Beyond the Sampled Token: Preserving Candidate Support in RLVR

2025-10-16 · Ruotian Peng, Yi Ren, Zhouliang Yu, Weiyang Liu 외 arxiv

We revisit exploration collapse in reinforcement learning with verifiable rewards (RLVR), from the perspective of the \emph{candidate distribution} for next-token prediction. We formally show that as probability concentr…

Reinforcement Learning