3 papers
cs.LG2026
Routing Without Embeddings: Fast And Interpretable Routing With Regular Expressions
Yifan Lu, Qiyue Zhang, Haotian Shan +2
Large Language Model (LLM) routers commonly rely on neural query embeddings, with larger encoders expected to better capture query intent and difficulty. Yet scaling Qwen2.5 encode…
cs.LG2026
Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems
Jiamu Zhang, Lingxi Zhang, Pengjun Lu +6
Efficiency is increasingly important for Large Language Model (LLM)-based multi-agent systems (MAS), as larger models and more agents introduce substantial execution costs. Recent…
cs.LG2026
The Routing Plateau: Understanding the Accuracy Limits of LLM Routers
Yifan Lu, Qiyue Zhang, Shenrun Zhang +4
LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by adaptively selecting a model for each query. Recent work has explored a broad ran…