让大模型对话更聪明：用长远规划选最优模型组合
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
- 基于蒙特卡洛树搜索探索多轮对话中不同模型选择的路径
- 在开放域和特定领域任务中，任务成功率显著超越单一模型和现有基线
- 无需在线搜索即可实现多轮高效路由，适合资源受限场景
多轮对话是与大语言模型交互的主要形式。尽管单轮模型路由有效，但现有方法因交互动态和延迟奖励，难以在多轮对话中最大化累积性能。为此，我们从短视的单轮选择转向长时序的序列化路由。提出DialRouter，先通过蒙特卡洛树搜索（MCTS）探索由不同模型选择引发的对话分支，收集高累积奖励轨迹；再利用搜索生成的数据学习轻量级路由策略，结合检索式未来状态近似，实现无需在线搜索的多轮路由。在开放域与特定领域对话任务上，使用开源与闭源模型组合进行实验，结果表明DialRouter显著优于单个模型及现有路由基线，在任务成功率上表现突出，并在结合成本感知奖励时取得更优的性能-成本权衡。
原文摘要 · Abstract (English)
Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maximize cumulative performance in multi-turn dialogue due to interaction dynamics and delayed rewards. To address this challenge, we move from myopic, single-turn selection to long-horizon sequential routing for multi-turn dialogue. Accordingly, we propose DialRouter, which first performs MCTS to explore dialogue branches induced by different LLM selections and collect trajectories with high cumulative rewards. DialRouter then learns a lightweight routing policy from search-derived data, augmented with retrieval-based future state approximation, enabling multi-turn routing without online search. Experiments on both open-domain and domain-specific dialogue tasks across diverse candidate sets of both open-source and closed-source LLMs demonstrate that DialRouter significantly outperforms single LLMs and existing routing baselines in task success rate, while achieving a superior performance-cost trade-off when combined with a cost-aware reward.
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。