Agent-as-a-Router: Agentic Model Routing for Coding Tasks
National University of Singapore(新加坡国立大学);DAMO Academy, Alibaba Group(阿里巴巴达摩院);University of California, Berkeley(加州大学伯克利分校);The Hong Kong University of Science and Technology(香港科技大学);Zhejiang University(浙江大学)
Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.
Agentic Router: An Execution-Grounded Continual Learning Approach With Memory
Zhejiang University(浙江大学);Zhejiang Lab(之江实验室);State Grid Hebei Electric Power Co., Ltd.(国网河北省电力有限公司);Macau University of Science and Technology(澳门科技大学)
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
School of Electronic and Computer Engineering, Peking University(电子与计算机工程学院,北京大学);Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University(广东省超高清沉浸媒体技术重点实验室,北京大学深圳研究生院)
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Gradient;Soochow University(苏州大学);Independent Researcher(独立研究者);University of Southern California(南加州大学);Rice University(Rice大学);Carnegie Mellon University(卡内基梅隆大学);Shanghai Jiao Tong University(上海交通大学);University of California, Berkeley(加州大学伯克利分校);University of the Chinese Academy of Sciences(中国科学院大学);University of California, Los Angeles(加州大学洛杉矶分校)
T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning
College of Artificial Intelligence, Tsinghua University(清华大学人工智能学院);State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院)
Where Is the Cost of Third-Party API Routers in Agentic Software Development?
School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);School of Software, Beihang University(北京航空航天大学软件学院);School of Computer Science, Peking University(北京大学计算机科学学院)
研究第三方 API 路由器在代理软件开发中的影响,通过实证研究编码代理中路由器端注入的四个干预级别,开发 SIDEL 框架评估代理,发现路由器端干预难测,客户端缓解措施未完全恢复控制,强调需提供商端输出完整性保证。
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机学院,北京大学);LLM-Core Xiaomi(小米LLM-Core)
Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training
NAVER Applied AI Group(NAVER应用人工智能集团);Healthcare AI Research Institute (HARI), Seoul National University Hospital(首尔大学医院医疗人工智能研究所(HARI));NAVER AI Lab(NAVER人工智能实验室)
Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
Anyscale(安尼斯科尔公司);Mississippi State University(密西西比州立大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Institute of AI for Industries, Chinese Academy of Sciences(中国科学院产业人工智能研究院)
IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(人工智能研究院,合肥综合性国家科学中心);School of Computing, National University of Singapore(计算学院,新加坡国立大学);NetEase Fuxi AI Lab(网易伏羲AI实验室)
School of Software and Microelectronics, Peking University(北京大学软件与微电子学院);College of Cyber Science, Nankai University(南开大学网络空间安全学院);The University of Western Australia(西澳大学)
CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
Qingdao Institute of Software, College of Computer Science;Technology, China University of Petroleum (East China);Shandong Key Laboratory of Intelligent Oil \& Gas Industrial Software;School of computing;artificial intelligence, Southwest Jiaotong University;Computer Engineering Department, University of Houston
VL-RouterBench: A Benchmark for Vision-Language Model Routing
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University(1 图像处理与模式识别研究所,上海交通大学);The Hong Kong University of Science and Technology (Guangzhou)(2 香港科学与技术大学(广州));The Hong Kong University of Science and Technology(3 香港科学与技术大学)
GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
School of Computer Science(计算机科学学院);Georgia Institute of Technology(佐治亚理工学院);Department of Electrical Engineering(电气工程系);Tsinghua University(清华大学);School of Electrical and Computer Engineering(电气与计算机工程学院)
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Southern University of Science and Technology(南方科技大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学)
Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
Key Laboratory of Symbolic Computation and Knowledge Engineering, MoE, Jilin University(符号计算与知识工程重点实验室,MoE,吉林大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Shanghai Jiao Tong University(上海交通大学);GAIR;Alibaba Group(阿里巴巴集团);University of Science and Technology of China(中国科学技术大学);Shanghai Innovation Institute(上海创新研究院)