让大模型在推理时自动并行处理独立任务，提速近半。
SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
- 通过重构思维链为分轮规划与并行执行，实现动态并行。
- 长推理任务减少39%序列生成token，数学等任务性能不变。
- 跨数据集有效，适合需要长推理的复杂问题求解场景。
大型推理模型（LRMs）在复杂推理任务中表现优异，但通常生成冗长的串行思维链，导致推理时间过长。为解决此问题，我们提出SPRINT，一种后训练和推理时框架，使LRMs能在推理过程中动态识别并利用并行化机会。SPRINT引入创新的数据整理流程，将自然语言推理轨迹重新组织为长周期规划与并行执行的结构化轮次。通过少量此类数据微调，模型学会在长推理过程中动态识别独立子任务并有效并行执行。大量评估表明，经SPRINT微调的模型在数学等复杂领域表现与原模型相当，同时在输出超过8000个标记的问题上，序列标记数减少最多达39%。此外，对两个分布外任务GPQA和Countdown的测试显示，平均序列标记数分别减少45%和65%，且性能保持一致。
原文摘要 · Abstract (English)
Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce SPRINT, a novel post-training and inference-time framework designed to enable LRMs to dynamically identify and exploit opportunities for parallelization during their reasoning process. SPRINT incorporates an innovative data curation pipeline that reorganizes natural language reasoning trajectories into structured rounds of long-horizon planning and parallel execution. By fine-tuning LRMs on a small amount of such curated data, the models learn to dynamically identify independent subtasks within extended reasoning processes and effectively execute them in parallel. Through extensive evaluations, we demonstrate that models fine-tuned with the SPRINT framework match the performance of reasoning models on complex domains such as mathematics while generating up to 39% fewer sequential tokens on problems requiring more than 8,000 output tokens. Finally, we observe consistent results transferred to two out-of-distribution tasks, namely GPQA and Countdown, with up to 45% and 65% reduction in average sequential tokens respectively for longer reasoning trajectories, while matching the performance of the fine-tuned reasoning model.
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。