让大模型自动分配思考资源，又快又省。
SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
- 模型自估任务复杂度，动态分配思考长度。
- 数学推理任务平均减少61%输出长度，准确率不变。
- 用户可预设思考量，实时掌控生成进度。
近期的大规模推理模型在各类任务中表现卓越，但即使面对简单问题也消耗大量令牌，造成资源浪费和用户延迟。为解决此问题，我们提出 SelfBudgeter——一种自适应的高效可控推理策略。首先，训练模型根据查询内容自估计所需推理预算；随后引入预算引导的 GRPO 进行强化学习，有效在保持准确率的同时压缩输出长度。实验表明，SelfBudgeter 能根据问题复杂度动态分配预算，在数学推理任务上实现平均响应长度压缩 61%，同时保持准确率。此外，该方法使用户可预估生成耗时并决定是否继续或终止，也可直接设定令牌预算来控制推理长度。
原文摘要 · Abstract (English)
Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this challenge, we propose SelfBudgeter - a self-adaptive reasoning strategy for efficient and controllable reasoning. Specifically, we first train the model to self-estimate the required reasoning budget based on the query. We then introduce budget-guided GRPO for reinforcement learning, which effectively maintains accuracy while reducing output length. Experimental results demonstrate that SelfBudgeter dynamically allocates budgets according to problem complexity, achieving an average response length compression of 61% on math reasoning tasks while maintaining accuracy. Furthermore, SelfBudgeter allows users to see how long generation will take and decide whether to continue or stop. Additionally, users can directly control the reasoning length by setting token budgets upfront.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。