Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Evaluating LLMs as Agentic Workflow Executors in Real-World Customer Support Skills
Md Tahmid Rahman Laskar, Gundeep Singh, Xue-Yong Fu +11
Enterprise customer-support agents increasingly rely on Large Language Models (LLMs) to execute bounded, tool-using workflows. We study this problem through the lens of Skill LLMs:…
cs.CL2026
When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success
Md Tahmid Rahman Laskar, Xue-Yong Fu, Gundeep Singh +11
Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is scored against a reference. W…