28 citations · 28 across the 4 of their papers we have counts for
5 papers
Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models
Utkarsh Soni, Syed Shariyar Murtaza, Yifan Nie +2
Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop…
When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents
Syed Shariyar Murtaza, Yifan Nie, Utkarsh Soni +2
LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large repositories a critical challenge. We present a production skill router over…
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti +4
Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-…
Regex-augmented Domain Transfer Topic Classification based on a Pre-trained Language Model: An application in Financial Domain
Vanessa Liao, Syed Shariyar Murtaza, Yifan Nie +1
A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialize…
Using entropy measures for comparison of software traces
A. V. Miranskyy, M. Davison, M. Reesor +1
The analysis of execution paths (also known as software traces) collected from a given software product can help in a number of areas including software testing, software maintenan…