# AdaSR： 自适应流式推理框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-12 08:00
- AIHOT 分数：48
- AIHOT 链接：https://aihot.virxact.com/items/cmqetakp005fgslun06k0p61r
- 原文链接：https://arxiv.org/abs/2606.14694

## AI 摘要

AdaSR 是一个自适应流式推理框架，使大语言模型在输入持续到达时边接收边思考，并在流结束后进行最终推敲。它引入分层相对策略优化（HRPO），将策略优化分解为流式推理和深度推理两阶段，提供更细粒度的优势分配，取代传统单一序列级奖励。HRPO 综合格式、准确性和自适应思考奖励，确保推理协议有效、保持最终性能并鼓励延迟感知的计算分配。实验表明，相比监督微调基线，AdaSR 在推理准确性、计算效率和流式延迟间取得更优平衡。代码已开源。

## 正文

Large reasoning models typically follow a read-then-think paradigm: they observe the complete input, reason over a static context, and then produce the answer. Yet many real-world scenarios are inherently dynamic, such as audio and video stream, where information arrives as a continuous stream and models must reason, update, and respond under partial observations. Recent streaming reasoning methods allow models to think while reading, but they largely rely on supervised imitation of pre-constructed trajectories, which limits their flexibility. In this paper, we propose AdaSR, an adaptive streaming reasoning framework that enables models to reason during input streaming and perform final deliberation once the stream is complete, learning when to think, and how much computation to allocate across different stages. To optimize this hierarchical reasoning process, we introduce Hierarchical Relative Policy Optimization (HRPO), which decomposes policy optimization into streaming reasoning and deep reasoning phases, providing more fine-grained advantage assignment instead of uniformly distributing a single sequence-level advantage over all tokens. HRPO integrates format, accuracy, and adaptive thinking rewards to enforce valid reasoning protocols, preserve final task performance, and encourage latency-aware computation allocation. Experiments show that AdaSR achieves a better balance among reasoning accuracy, computational efficiency, and streaming latency compared with supervised fine-tuning baseline. We release our code at https://github.com/EIT-NLP/StreamingLLM/tree/main/AdaSR.