Rajan Agarwal
I'm a Software Engineering student at Waterloo. I care a lot about scaling RL for coding, compute-efficient language models, computer vision, and automating more of the research loop. Recently, I've worked with teams of incredible people at Thinking Machines, Proximal, Amazon AGI, and Thoughtful Lab.
Reach out! I always want to meet more people with controversial opinions, fun stories and new ideas. I am most active on:
Notable Work
- FrontierSWE(Apr 2026)
Ultra long-horizon coding agent benchmark for engineering and research.
- Amazon Nova Act(Dec 2025)
RL for Amazon Nova Act, a browser-use agent. Co-led enterprise performance.
Related:Amazon RL Training - LLMs invent compression(Nov 2025)
Discrete compression schemes learned by LLMs for long-context compaction.
Related:Deep Learning with Yacine - Natural deception with RL(Nov 2025)
Hidden-information game agents trained with RL and studied for emergent deception.
Multilingual alignment through encoder injection under Cohere Labs.
- Shadow(Aug 2025)
Open-source background coding agent that runs in isolated environments. 1.5k+ Stars.