← Search

Santhoshi Ravichandran

1 accepted papers

2025

How to Train Your LLM Web Agent: A Statistical Diagnosis

NeurIPS 2025poster

Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary agents. Bridging this gap is key to enabling customizable, efficient, and privacy-preserving agents. Two challenges hinder progress: the reproducibility issues in RL and L…

Cited by 0SourceScholar