用轻量模型协作推理，大幅降低大模型计算成本。
When Less is Enough: Efficient Inference via Collaborative Reasoning
- 大模型生成推理信号，轻量模型解读并输出答案。
- 在AIME和GPQA上减少60%的输出令牌，性能不降。
- 适合需要高效推理的应用场景，如移动端部署。
本文提出DUET（双模型高效两阶段推理）框架，通过能力较强的模型与轻量模型协同完成任务。传统单一大模型端到端推理耗时耗力，而DUET将推理分为两阶段：强模型生成推理信号，轻量模型基于该信号生成最终答案，使复杂推理由强模型处理，非推理部分交由轻量模型，兼顾性能与效率。为此，我们设计长度惩罚联合训练目标，促使强模型仅传递任务所需信息。实验表明，相较于单独使用大模型，DUET在AIME和GPQA等复杂推理基准上可节省高达60%的大模型输出令牌，同时保持优异推理性能。
原文摘要 · Abstract (English)
In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform end-to-end reasoning and prediction often incurs substantial inference cost. In contrast, DUET decomposes inference into two stages: the capable model produces a reasoning signal, and the lightweight model interprets this signal to generate the final answer, allowing reasoning-intensive computation to be handled by the capable model while non-reasoning-intensive components are delegated to the lightweight model without sacrificing task performance. To achieve this objective, we propose a length-penalized joint training objective that encourages the capable model to transmit only the information that is sufficient for the lightweight model to solve the task. As a result, DUET maintains strong reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone, saving up to 60% of the large model's output tokens on challenging reasoning benchmarks, including AIME and GPQA.
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。