ProgRouter：面向质量-成本权衡的多智能体大语言模型工作流的在线进度引导编排
ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
浏览论文内容
中文总结 AI 辅助
ProgRouter是一种在线进度引导路由框架，通过多视图任务进度评分器等机制，在多智能体LLM工作流中平衡任务质量与时间、成本预算，在多类任务数据集上较基线降低运营成本且保持性能。
中文摘要 AI 辅助
多智能体大语言模型（LLM）工作流已成为一种强大的范式，通过专门的LLM智能体之间的协作推理来解决复杂、开放式任务，但由于重复调用LLM和长期上下文积累，它们会产生大量运营成本。现有的级联路由方法会做出一次性的、查询级别的决策，无法适应多步骤工作流的动态性和状态依赖性，在多步骤工作流中，每一步选择合适的LLM取决于不断变化的任务进度、剩余任务难度和成本效率要求。我们提出了ProgRouter，这是一种在线进度引导路由框架，可在遵守时间和成本预算的同时，自适应选择工作流各步骤的LLM智能体，以保持任务解决质量。ProgRouter引入了多视图任务进度评分器，该评分器将粗略的工作流结果状态与子任务完成、进度趋势和工作流状态质量的细粒度信号相结合；随后，双路径任务进度预测器和自适应元门控机制会估计每个候选路由LLM的进度增益。ProgRouter会做出在线的分步路由决策，以平衡进度增益、任务时间预算和长期运营成本效率。在HumanEval Plus、MBPP、MATH-500和ASQA上进行的实验涵盖了智能体代码生成、数学推理和检索增强的长形式问答，结果表明，与关键基线相比，ProgRouter降低了运营成本，同时保持了强大的任务解决性能。
英文摘要
Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRouter, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets. ProgRouter introduces a multi-view task progress scorer that combines coarse workflow outcome regimes with fine-grained signals on subtask completion, progress trends, and workflow state quality. Then, a dual-path task progress predictor and an adaptive meta-gating mechanism estimate the progress gain for each candidate routed LLM. ProgRouter makes online step-wise routing decisions that balance progress gain, task time budgets, and long-term operating cost efficiency. Experiments on HumanEval Plus, MBPP, MATH-500, and ASQA, spanning agentic code generation, mathematical reasoning, and retrieval-augmented long-form question answering, demonstrate that ProgRouter reduces the operating cost relative to key baselines while maintaining strong task-solving performance.
发表机构
- Aston University（阿斯顿大学）
- Queen Mary University of London（伦敦玛丽女王大学）
- University of Exeter（埃克塞特大学）
机构由 AI 辅助整理，请以论文原文为准。
