3 papers
cs.CL2026
: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
Muyu He, Adit Jain, Anand Kumar +4
As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from…
cs.SE2025
Intuition to Evidence: Measuring AI's True Impact on Developer Productivity
Anand Kumar, Vishal Khare, Deepak Sharma +8
We present a comprehensive real-world evaluation of AI-assisted software development tools deployed at enterprise scale. Over one year, 300 engineers across multiple teams integrat…
cs.SE2025
DeputyDev -- AI Powered Developer Assistant: Breaking the Code Review Logjam through Contextual AI to Boost Developer Productivity
Vishal Khare, Vijay Saini, Deepak Sharma +3
This study investigates the implementation and efficacy of DeputyDev, an AI-powered code review assistant developed to address inefficiencies in the software development process. T…