Work

AdapThink: Adaptive Thinking Preferences for Reasoning Language Models

Year: 2026

Type: conference-paper

Abstract: The "slow thinking" paradigm has been widely validated to enhance the reasoning capabilities of Large Language Models (LLMs), but it introduces notable reasoning inefficiencies: models often overthink simple tasks while prematurely shifting their reasoning paths when addressing complex problems.To address this, we propose AdapThink, a simple yet efficient framework for adaptive reasoning preference control.Unlike methods imposing uniform length constraints, AdapThink dynamically adjusts reflection preferences based on grouplevel distributional statistics of reasoning length and reflection intensity.We further introduce a dispersion-based diversity sampling mechanism that maximizes the geometric spread of reasoning patterns, accelerating learning through exposure to diverse problem-solving strategies.Across mathematical reasoning and code generation benchmarks, AdapThink reduces average response length by 17.1%-21.4%while improving performance by 6.12-6.59points under 32K token budgets, demonstrating superior efficiency and robustness against reward hacking compared to strong baselines.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.477