3 papers
cs.AI2026
When Routing Collapses: On the Degenerate Convergence of LLM Routers
Guannan Lai, Han-Jia Ye
LLM routing aims to achieve a favorable quality--cost trade-off by dynamically assigning easy queries to smaller models and harder queries to stronger ones. However, across both un…
cs.AI2026
MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing
Haoxuan Ma, Guannan Lai, Han-Jia Ye
Multimodal large language models (MLLMs) have advanced rapidly, yet heterogeneity in architecture, alignment strategies, and efficiency means that no single model is uniformly supe…
cs.SE2025
Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration
Yanbin Zhang, Hanhui Ye, Yue Bai +4
Workflow automation promises substantial productivity gains in everyday document-related tasks. While prior agentic systems can execute isolated instructions, they struggle with au…