arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.03092cs.AI
收藏

推理的影子价格:LLM最优预算分配的经济学视角

The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs

University of Science and Technology of China(中国科学技术大学)

Xu Wan, Speed Zhu, Jianwei Cai, Guang Chen, XiMing Huang, Wiggin Zhou, Mingyang Sun

AI总结:

本文从经济学视角将推理预算分配建模为全局约束优化问题,提出基于影子价格的CLEAR方法,通过理性放弃和资源再分配,在资源稀缺下显著提升总token成本与平均准确率的帕累托前沿。

摘要:

推理时扩展已成为提升大型语言模型性能的关键途径,但实际部署受严格计算预算限制。本文将推理预算分配建模为受经济学原理支配的全局约束优化问题。通过使用移位激增函数对每查询推理效用建模,我们推导出基于全局影子价格的最优分配策略,该价格在资源稀缺下均衡边际效用。基于此理论,我们提出约束潜在效用均衡分配推理(CLEAR)。它执行理性放弃,并将资源从无力偿付的查询重新分配到接近其涌现阈值的可解查询。在不同流量流的多个推理任务上的大量实验表明,CLEAR显著改善了总token成本与平均准确率的帕累托前沿。在资源稀缺模式下,与均匀分配相比,CLEAR的全局准确率提升高达3倍。

英文摘要:

Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for Reasoning (CLEAR). It performs rational abandonment and reallocates resources from insolvent queries to solvable queries near their emergence thresholds. Extensive experiments on several reasoning tasks with different traffic streams demonstrate that CLEAR significantly improves the Pareto frontier of total token cost versus mean accuracy. In resource-scarce regimes, CLEAR achieves up to a 3x improvement in global accuracy compared to uniform allocation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑