3 papers
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…
cs.CL2025
DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations
Elena Khasanova, Harsh Saini, Md Tahmid Rahman Laskar +3
The rapid advancements in Large Language Models (LLMs) have enabled their adoption in real-world industrial scenarios for various natural language processing tasks. However, the hi…
cs.CL2025
DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization
Xue-Yong Fu, Elena Khasanova, Md Tahmid Rahman Laskar +2
Large language models (LLMs) have achieved impressive performance in text summarization, yet their performance often falls short when applied to specialized domains that differ fro…