Prithviraj Ammanabrolu

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

How Reasoning Evolves from Post-Training Data in Sequential Decision-Making Domains

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning

Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning

TALES: Text Adventure Learning Environment Suite

Long Grounded Thoughts: Distilling Compositional Visual Reasoning Chains at Scale

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

Setting the DC: Tool-Grounded D&D Simulations to Test LLM Agents

In-context Ranking Preference Optimization

A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models

Critique-out-Loud Reward Models