动态分配模型与推理策略，高效完成复杂推理任务。
Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection
- 根据任务难度自适应选择模型和推理策略
- 在相同预算下准确率更高，令牌消耗降低60%以上
- 支持任意模型与策略的即插即用，灵活易扩展
语言模型（LM）的内在能力及其采用的推理策略共同决定其在推理任务中的表现。尽管测试时扩展被视为应对复杂推理任务的有效方法，但会带来高昂计算成本，并常导致“过度思考”，使模型陷入“思维陷阱”。为此，我们提出路由至推理（RTR），一种新型统一路由框架，可在预算约束下根据任务难度动态分配语言模型和推理策略。RTR学习专家模型与推理策略的压缩表示，实现在推理时联合且自适应的选择。该方法成本低、灵活性高，可无缝扩展至任意黑盒或白盒模型及策略，实现真正的即插即用。在七种开源模型和四种推理策略上的大量实验表明，RTR在所有基线中实现了准确率与计算效率的最佳权衡，优于最优单模型，同时令牌使用量减少超过60%。
原文摘要 · Abstract (English)
The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning tasks, it incurs substantial computational costs and often leads to "overthinking", where models become trapped in "thought pitfalls". To address this challenge, we propose Route-To-Reason (RTR), a novel unified routing framework that dynamically allocates both LMs and reasoning strategies according to task difficulty under budget constraints. RTR learns compressed representations of both expert models and reasoning strategies, enabling their joint and adaptive selection at inference time. This method is low-cost, highly flexible, and can be seamlessly extended to arbitrary black-box or white-box models and strategies, achieving true plug-and-play functionality. Extensive experiments across seven open source models and four reasoning strategies demonstrate that RTR achieves an optimal trade-off between accuracy and computational efficiency among all baselines, achieving higher accuracy than the best single model while reducing token usage by over 60%.
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。