activity
20242026
collaborators

7 papers

cs.AI2026

Knowledge-Centric Self-Improvement

Xuefei Julie Wang, Lauren Hyoseo Yoon, Chengrui Qu +4

Self-improving AI systems typically treat the agent as the object that improves, by optimizing prompts, workflows, harnesses, or even the agent's own code. This agent-centric view…

cs.SE2026

FormulaCode: Evaluating Agentic Optimization on Large Codebases

Atharva Sehgal, James Hou, Akanksha Sarkar +4

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realisti…

cs.AI2026

Programmatic Context Augmentation for LLM-based Symbolic Regression

Hao Liu, Xiao-Wen Yang, Atharva Sehgal +4

Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional…

cs.CV2025

Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization

Xuefei, Wang, Kai A. Horstmann +9

Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large a…

cs.CV2025

Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor

Ethan Lin, Linxi Zhao, Atharva Sehgal +1

Text-based visual descriptors--ranging from simple class names to more descriptive phrases--are widely used in visual concept discovery and image classification with vision-languag…

cs.CV2025

Self-Evolving Visual Concept Library using Vision-Language Critics

Atharva Sehgal, Patrick Yuan, Ziniu Hu +3

We study the problem of building a visual concept library for visual recognition. Building effective visual concept libraries is challenging, as manual definition is labor-intensiv…