2 papers
cs.AI2026
Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning
Akshay Arora, Ishan Nigam, Ashutosh Aggarwal +6
As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making. We introduce AgenticAI-Supervisor, an API…
cs.CL2026
RE-AD: Real-Time Requirement Adherence for Data Labeling
Siddarth Malreddy, Ishan Nigam, Akshay Arora +2
Human-annotated data remains fundamental to training frontier Large Language Models (LLMs). However, crowd-sourced annotations often suffer from quality issues stemming from annota…