paper-with-me

홈 › Papers

Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality

2025-08-16 · Ziqian Bi, Lu Chen, Junhao Song, Hongying Luo, Enze Ge, Junmin Huang, Tianyang Wang, Keyu Chen, Chia Xin Liang, Zihan Wei, Huafeng Liu, Chunjie Tian, Jibin Guan, Joe Yeong, Yongzhi Xu, Peng Wang, Xinyuan Song, Junfeng Hao arxiv

This study presents the first comprehensive evaluation of thinking budget mechanisms in medical reasoning tasks, revealing fundamental scaling laws between computational resources and reasoning quality. We systematically evaluated two major model families, Qwen3 (1.7B to 235B parameters) and DeepSeek-R1 (1.5B to 70B parameters), across 15 medical datasets spanning diverse specialties and difficulty levels. Through controlled experiments with thinking budgets ranging from zero to unlimited tokens, we establish logarithmic scaling relationships where accuracy improvements follow a predictable pattern with both thinking budget and model size. Our findings identify three distinct efficiency regimes: high-efficiency (0 to 256 tokens) suitable for real-time applications, balanced (256 to 512 tokens) offering optimal cost-performance tradeoffs for routine clinical support, and high-accuracy (above 512 tokens) justified only for critical diagnostic tasks. Notably, smaller models demonstrate disproportionately larger benefits from extended thinking, with 15 to 20% improvements compared to 5 to 10% for larger models, suggesting a complementary relationship where thinking budget provides greater relative benefits for capacity-constrained models. Domain-specific patterns emerge clearly, with neurology and gastroenterology requiring significantly deeper reasoning processes than cardiovascular or respiratory medicine. The consistency between Qwen3 native thinking budget API and our proposed truncation method for DeepSeek-R1 validates the generalizability of thinking budget concepts across architectures. These results establish thinking budget control as a critical mechanism for optimizing medical AI systems, enabling dynamic resource allocation aligned with clinical needs while maintaining the transparency essential for healthcare deployment.

📄 PDF Abstract BibTeX arXiv:2508.12140

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How Far Are We from Optimal Reasoning Efficiency?

2025-06-08 · Jiaxuan Gao, Shu Yan, Qixin Tan, Lu Yang 외

Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency …

16kBenchmarkingNumerical Integration

Rethinking the shape convention of an MLP

2025-10-02 · Meng-Hsi Chen, Yu-Ang Lee, Feng-Ting Liao, Da-shan Shiu arxiv

Multi-layer perceptrons (MLPs) conventionally follow a narrow-wide-narrow design where skip connections operate at the input/output dimensions while processing occurs in expanded hidden spaces. We challenge this conventi…

Computational Efficiency

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

2025-05-19 · Penghui Qi, Zichen Liu, Tianyu Pang, Chao Du 외

Scaling test-time compute is crucial for enhancing the reasoning capabilities of large language models (LLMs). Existing approaches typically employ reinforcement learning (RL) to maximize a verifiable reward obtained at …

Mathematical ReasoningReinforcement Learning (RL)

Steering LLM Thinking with Budget Guidance

2025-06-16 · Junyan Li, Wenshuo Zhao, Yang Zhang, Chuang Gan

Recent deep-thinking large language models often reason extensively to improve performance, but such lengthy reasoning is not always desirable, as it incurs excessive inference costs with disproportionate performance gai…

Math

Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs

2026-03-29 · Amirul Rahman, Aisha Karim, Kenji Nakamura, Yi-Fan Ng arxiv

Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, existing approaches optimize reasoning under fixed or uniformly sampled …

Mathematical Reasoning