paper-with-me

홈 › Papers

Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries

2025-10-09 · Marius Dragoi, Ioana Pintilie, Florin Gogianu, Florin Brad arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm to improve Large Language Models on reasoning tasks such as coding, math or logic. To assess the reasoning boundary (the fraction of problems a model can solve) researchers often report Pass@k at large sampling budgets. Recent results reveal a crossover phenomenon: while RLVR models outperform the base model at small k values, the base model usually outperforms them when sampling a very large number of completions. This has been interpreted as evidence that base models have a larger reasoning boundary. We argue that on tasks with discrete answer spaces, such as math with numeric outputs, Pass@k at large k reflects the increasingly higher chance of success in the limit of the number of trials rather than genuine reasoning, and can therefore be misleading. We propose Cover@tau, which measures the fraction of problems that a model can solve for which at least a tau proportion of completions are correct. Unlike Pass@k, Cover@tau captures reasoning under an explicit reliability threshold: models that rely on random guessing degrade rapidly as tau increases. We evaluate several RLVR models using Cover@tau-based metrics and illustrate how the relative rankings of popular algorithms change compared to Pass@1, offering a different perspective on reasoning boundaries.

📄 PDF Abstract BibTeX arXiv:2510.08325

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

2025-08-19 · Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang 외 arxiv

Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lack of exploration in two key areas: Depth…

Reinforcement Learning

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models

2026-03-02 · Qiyuan Zhang, Yufei Wang, Tianhe Wu, Can Xu 외 arxiv

Recent advancements in Generative Reward Models (GRMs) have demonstrated that scaling the length of Chain-of-Thought (CoT) reasoning considerably enhances the reliability of evaluation. However, current works predominant…

Reinforcement Learning

Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks

2025-09-26 · Miao Jing, Mengting Jia, Junling Lin, Zhongxia Shen 외 arxiv

Recent advances in vision-language models (VLMs) have achieved remarkable performance on standard medical benchmarks, yet their true clinical reasoning ability remains unclear. Existing datasets predominantly emphasize c…

Semantic Similarity

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs

2025-02-15 · Zongqian Wu, Tianyu Li, Jiaying Yang, Mengmeng Zhan 외

Deep iterative chain-of-thought (CoT) reasoning enables LLMs to tackle complex tasks by progressively activating relevant pre-trained knowledge. However, it faces challenges in ensuring continual improvement and determin…

AllDiversity

Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach

2025-03-13 · Afrar Jahin, Arif Hassan Zidan, Wei zhang, Yu Bao 외

With the rapid advancement of Artificial Intelligence (AI), Large Language Models (LLMs) have significantly impacted a wide array of domains, including healthcare, engineering, science, education, and mathematical reason…

Formal LogicMathematical ReasoningMMLU