3 papers
physics.soc-ph2026
Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
Rana Muhammad Usman, Dominic Williamson
Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted social-platform testbed, and re…
cs.LG2026
PhantomFill: When the Form Demands an Answer, Language Models Invent One
Rana Muhammad Usman
Language models in production do not write prose. They fill forms: JSON fields, function arguments, extraction templates. We show that the form itself causes hallucination. We ask…
cs.AI2026
Counterfactual Evidence Audits Predict LLM-Agent Susceptibility to Ranked Context
Rana Muhammad Usman
LLM agents increasingly decide from evidence assembled by upstream systems: retrievers choose documents, recommenders choose posts, and memory systems choose prior events. Existing…