TCAndon路由器：面向多智能体协作的自适应推理路由系统

TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration

January 8, 2026

作者: Jiuzhou Zhao, Chunrong Chen, Chenqi Qiao, Lebin Zheng, Minqi Han, Yanchi Liu Yongzhou Xu Xiaochuan Xu Min Zhang

cs.AI

摘要

多智能体系统（MAS）已成为构建高性能智能应用的重要范式。在这些系统中，负责确定应由哪些专家智能体处理查询的路由器对整体性能起着关键作用。现有路由策略主要分为两类：性能路由（通过平衡不同规模模型间的延迟与成本）和任务路由（将查询分配给领域专家以提高准确性）。在企业实际应用中，任务路由更为适用；然而现有方案多依赖静态单标签决策，这会带来两大局限：（i）难以在业务领域扩展时无缝集成新智能体；（ii）因智能体能力重叠引发路由冲突，最终降低准确性与鲁棒性。 为解决这些挑战，我们提出TCAndon-Router（TCAR）：一种面向多智能体协作的自适应推理路由器。与传统路由器不同，TCAR支持动态智能体接入，并会首先生成自然语言推理链，再预测能够处理查询的候选智能体集合。此外，我们设计了协作执行流程：被选中的智能体独立生成响应后，由专职优化智能体进行聚合提炼，最终形成高质量统一响应。 在公开数据集和企业真实数据上的实验表明，TCAR能显著提升路由精度、减少路由冲突，并在模糊场景中保持鲁棒性。我们已在https://huggingface.co/tencent/TCAndon-Router 发布TCAR，以支持可解释协作式多智能体路由的未来研究。

English

Multi-Agent Systems(MAS) have become a powerful paradigm for building high performance intelligent applications. Within these systems, the router responsible for determining which expert agents should handle a given query plays a crucial role in overall performance. Existing routing strategies generally fall into two categories: performance routing, which balances latency and cost across models of different sizes, and task routing, which assigns queries to domain-specific experts to improve accuracy. In real-world enterprise applications, task routing is more suitable; however, most existing approaches rely on static single-label decisions, which introduce two major limitations: (i) difficulty in seamlessly integrating new agents as business domains expand, and (ii) routing conflicts caused by overlapping agent capabilities, ultimately degrading accuracy and robustness.To address these challenges, we propose TCAndon-Router(TCAR): an adaptive reasoning router for multi-agent collaboration. Unlike traditional routers, TCAR supports dynamic agent onboarding and first generates a natural-language reasoning chain before predicting a set of candidate agents capable of handling the query. In addition, we design a collaborative execution pipeline in which selected agents independently produce responses, which are then aggregated and refined into a single high-quality response by a dedicated Refining Agent.Experiments on public datasets and real enterprise data demonstrate that TCAR significantly improves routing accuracy, reduces routing conflicts, and remains robust in ambiguous scenarios. We have released TCAR at https://huggingface.co/tencent/TCAndon-Router to support future research on explainable and collaborative multi-agent routing.