analiza aiqbench
This research introduces CLEAR, an optimization framework that applies economic shadow pricing to dynamically allocate inference budgets between solvable and insolvent queries. By shifting resources away from failing attempts, the method achieves up to a 3x improvement in global accuracy under resource-scarce conditions compared to uniform allocation. For production systems facing strict computational constraints, this approach offers a theoretically grounded strategy to maximize the Pareto frontier of cost versus accuracy.
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
arXiv:2606.03092v2 Announce Type: replace Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2606.03092 [cs.AI]
(or arXiv:2606.03092v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.03092 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 233 cuvinte
Subiecte conexe
Sam Altman says it’s better for RAM to be in a data center than on your desk
The Verge · 30 oct. 2026
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
arXiv · 12 oct. 2026
To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
arXiv · 8 iun. 2026
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
arXiv · 3 iun. 2026