Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs

Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha, Dilek Hakkani-Tür, Hao Peng

SAI review preview

SAI reviewed this ICML 2026 paper and its available research artifacts. Sign in to read the complete referee report, inline feedback, and execution-based verification where available.

29Detailed review comments

CompletePaper and code review

2% of graded claims reproducedReplication status