Author

Pulkit Agrawal

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jul 2026

Prompt-Driven Exploration

Across manipulation and reasoning tasks, PDE enables RL to learn successful policies even from zero-reward starts, and improves sample efficiency more broadly.

Sunshine Jiang, John Marangola, David W. Zhang et al. · arXiv.org · 0 citations