Shahryar Sarkani

Identifiers

• name variant Shahryar Sarkani 0.60 · backfill

Papers (2)

1. EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms cs.LG · 2026 · author #3
2. When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control cs.LG · 2026 · author #4

Mentions

• 2606.04145 #3 · arxiv_oai · confidence 0.70 Shahryar Sarkani
• 2605.26418 #4 · arxiv_oai · confidence 0.70 Shahryar Sarkani

Frequent Coauthors

• Chuanyi Sun 2 shared papers
• Guilin Zhang 2 shared papers
• John Fossaceca 1 shared papers
• John M. Fossaceca 1 shared papers
• Kai Zhao 1 shared papers