Sagnik Mukherjee

I’m a PhD candidate at UIUC, working on Reinforcement Learning for LM post-training with Dilek Hakkani-Tür and Hao Peng. I was the first to discover emergent structures in on-policy training, which later spawned a research thread at the intersection of optimization and on-policy training in LLMs. Lately I’ve been thinking about agentic sequential decision making — specifically, the delayed consequences of actions and partial observability. Feel free to reach out if you’d like to collaborate or chat.

News

Sept 2026New preprint: Understanding LLM Parameter Update Sparsity through the Lens of Fisher — we explain, theoretically, why on-policy data causes sparse updates.

Sept 2026VASR was accepted at NeurIPS 2026.

Sept 2026Gave a talk, “Optimization Geometry in LLM Post-Training”, at the UIUC Machine Learning Seminar.

Jul 2026Presented Do We Need Adam? as an Oral at the ICML 2026 main conference in Seoul.

May 2026Started my internship at Microsoft Frontier Tuning, hosted by Harsh Jhamtani and Jacob Andreas.

Research Directions

Optimization in Post-Training

How does on-policy data shape the optimization landscape and training dynamics of language models? I study the structure that emerges during on-policy training—from sparse parameter updates to preserved spectral structure—and use these insights to develop more efficient methods for LLM post-training.

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models (NeurIPS 2025)
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs (ICML 2026 · Oral)
ISO: An RLVR-Native Optimization Stack (Preprint)
Understanding LLM Parameter Update Sparsity through the Lens of Fisher (Preprint)

Sequential Decision Making

How does the notion of “Delayed consequences of actions” and “Partial Observability” affect reasoning and decision making in LLMs?

cooking ;)

Mentoring

I have had the opportunity to work with some amazing students.

Pavan Jayasinha — now at OpenAI Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Yufan Zhang — visiting student at UIUC Understanding LLM Parameter Update Sparsity through the Lens of Fisher
Saket Vispute — student at IIT Bombay