2 papers
cs.LG2026
What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows
Shereen Anand, Ju Wang, Yali Du
An aggregate task score does not distinguish failures of scheduling, state retention, and candidate selection. We develop a small executable instrument that varies dependency depth…
cs.GT2026
Verification Allocation in Stylized LLM Agent Pipelines under Hidden Tool Degradation: A Discrete-Time Mean-Field Analysis
Shereen Anand, Chandramani Singh
We study a stylized verification-allocation model for role-structured pipelines with binary inherited corruption and hidden tool degradation. Standard contraction arguments give se…