Jayanth Srinivasa

Retrofitting Code Using LLMs to Support Exceptional Behavior

Linghan Zhong, Jiyang Zhang, Jayanth Srinivasa, et al.

CROCODIL: Cross-Model Code Editing with LLMs

Linghan Zhong, Aditya Thimmaiah, Jayanth Srinivasa, et al.

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

An Luo, Jin Du, Xun Xian, et al.

AgentDS is a benchmark that tests how well AI agents and humans working together can solve real-world data science problems across industries like healthcare, retail, and manufacturing. The research found that while AI agents alone perform poorly on these domain-specific tasks, human-AI collaboration produces the best results, showing that human expertise remains crucial even as AI becomes more advanced.

Context Bootstrapped Reinforcement Learning

Saaket Agashe, Jayanth Srinivasa, Gaowen Liu, et al.

This paper introduces Context Bootstrapped Reinforcement Learning (CBRL), a technique that helps AI models learn better by occasionally providing example demonstrations during training. The method starts by frequently showing examples to help the model explore and learn initial patterns, then gradually removes these examples so the model must eventually succeed on its own. The approach is tested on reasoning tasks and a specialized programming language, showing consistent improvements in success rates and learning efficiency.