Author

Shubham Gandhi

2 papers 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 Preprint Sep 2026

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a reward; they are scored o...

Shubham Gandhi, Saurabh Goyal, K. Kate et al. · 1 citation

#artificial intelligence Jun 2026

Steer, Don't Solve: Training Small Critic Models for Large Code Agents

A separate critic model that is specialized in high-level planning to steer the coding agent in inference and reduce the total inference costs for some coding agents by solving tasks in fewer steps is trained.

Shubham Gandhi, Yiqing Xie, Atharva Naik et al. · arXiv.org · 0 citations