7 papers
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…
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…
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…
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…
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…
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…