activity
20242026
collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI2026

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…

cs.AI2026

READY or Not: Reliable Enterprise Agent Deployment

Veronica Chatrath, Bryan Zhu, Jingxuan Fan +15

An AI agent can perform well on benchmarks and still be unsuitable for deployment. Existing AI-agent benchmarks measure whether an agent can complete realistic professional work, w…

cs.AI2026

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…

cs.AI2026

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,…

cs.AI2026

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

Akshay Manglik, Apaar Shanker, Kaustubh Deshpande +6

Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses pattern…

cs.AI2026

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…