一作ACL 2026Findings· Findings of ACL
Steering LLM Thinking with Budget Guidance
Junyan Li · Wenshuo Zhao · Yang Zhang · Chuang Gan
摘要
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...