collaborators

8 papers

cs.CR2026

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools

Bardia Mohammadi, Lars Klein, Akhil Arora +1

Tool-augmented language agents speculatively issue likely future tool calls to hide latency, but those calls leak inferred user intent to external services before the agent commits…

cs.AI2026

ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning

Nearchos Potamitis, Vansh Ramani, Har Ashish Arora +3

Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same model, strategy, and task can produce meaningfully different answers and costs across repeat…

cs.AI2026

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

Xavier Theimer-Lienhard, Mushtaha El-Amin, Fay Elhassan +5

Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDSS remain largely opaque. Mos…

cs.LG2026

Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows

Bardia Mohammadi, Nearchos Potamitis, Lars Klein +2

LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement trigger, so faults, speculation, and conc…

cs.CL2026

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety

Fay Elhassan, David Sasu, Alexandra Kulinkina +2

We evaluate whether clinician pairwise preferences provide a reliable signal of clinical safety in large language model (LLM) evaluation using expert feedback from MOOVE (Massive O…

cs.LG2026

MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support

Yusuf Kesmen, Fay Elhassan, Jiayi Ma +7

Large language models (LLMs) are increasingly used for conversational clinical decision support, yet they conflate next token prediction with probabilistic decision making. We argu…