Steering LLM Thinking with Budget Guidance

Junyan Li, Wenshuo Zhao, Yang Zhang, Chuang Gan


Abstract
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 gains. Controlling reasoning length without sacrificing performance is therefore important, but remains challenging, especially under tight thinking budgets. We propose budget guidance, a simple yet effective method for steering the reasoning process of LLMs toward a target budget without requiring any LLM fine-tuning. Our approach introduces a lightweight predictor that models a Gamma distribution over the remaining thinking length during next-token generation. This signal is then used to guide generation in a soft, token-level manner, ensuring that the overall reasoning trace adheres to the specified thinking budget. Budget guidance enables natural control of the thinking length, along with significant token efficiency improvements over baseline methods on challenging math benchmarks. For instance, it achieves up to a 26% accuracy gain on the MATH-500 benchmark under tight budgets compared to baseline methods, while maintaining competitive accuracy with only 63% of the thinking tokens used by the full-thinking model. Budget guidance also generalizes to broader task domains and exhibits emergent capabilities, such as estimating question difficulty. We release our code and model weights at https://github.com/UMass-Embodied-AGI/BudgetGuidance.
Anthology ID:
2026.findings-acl.1866
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
37437–37451
Language:
URL:
https://aclanthology.org/2026.findings-acl.1866/
DOI:
Bibkey:
Cite (ACL):
Junyan Li, Wenshuo Zhao, Yang Zhang, and Chuang Gan. 2026. Steering LLM Thinking with Budget Guidance. In Findings of the Association for Computational Linguistics: ACL 2026, pages 37437–37451, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Steering LLM Thinking with Budget Guidance (Li et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1866.pdf
Checklist:
 2026.findings-acl.1866.checklist.pdf