4 papers
GRPO Training Dynamics for Small Language Models
Rajat Ghosh, Vaishnavi Bhargava, Henry Wong +2
Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. How- ever, GRPO training dynami…
Predictable GRPO: A Closed-Form Model of Training Dynamics
Rajat Ghosh, Datta Nimmaturi, Aryan Singhal +4
We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO upda…
RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval
Pratik Shah, Rajat Ghosh, Aryan Singhal +1
General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system t…
BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning
Jinan Zhou, Rajat Ghosh, Vaishnavi Bhargava +2
When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no…