3 citations · 3 across the 7 of their papers we have counts for
7 papers
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
Vinay Samuel, Varun Ursekar, Vijay S. Kalmath +3
Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance…
CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR
Veronica Chatrath, Bryan Zhu, George Pu +16
Large language models perform strongly on medical knowledge benchmarks, but reliable clinical deployment requires agents to conduct defensible investigations over heterogeneous, lo…
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Varun Ursekar, Apaar Shanker, Yash Maurya +4
As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory,…
VeRO: A Harness for Agents to Optimize Agents
Varun Ursekar, Apaar Shanker, Veronica Chatrath +2
An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its releva…
Sparx: Distributed Outlier Detection at Scale
Sean Zhang, Varun Ursekar, Leman Akoglu
There is no shortage of outlier detection (OD) algorithms in the literature, yet a vast body of them are designed for a single machine. With the increasing reality of already cloud…
Predicting the future with a scale-invariant temporal memory for the past
Wei Zhong Goh, Varun Ursekar, Marc W. Howard
In recent years it has become clear that the brain maintains a temporal memory of recent events stretching far into the past. This paper presents a neurally-inspired algorithm to u…
Ion Crystal Metamorphoses in a Paul trap
V. Ursekar, J. M. Silvester, Y. S. Nam +1
The standard second-order pseudo-oscillator potential used in many analytical investigations of the properties of ions stored in a Paul trap has serious limitations. In this paper…