Rishabh Agarwal

The Art of Scaling Reinforcement Learning Compute for LLMs

Shape of Thought: When Distribution Can Matter More than Correctness in Reasoning Tasks

Process Reward Models That Think

Training Language Models to Self-Correct via Reinforcement Learning

Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

Towards Compute-Optimal Many-Shot In-Context Learning

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Not All LLM Reasoners Are Created Equal

Evolving Alignment via Asymmetric Self-Play

Generative Verifiers: Reward Modeling as Next-Token Prediction

Don’t Throw Away Data: Better Sequence Knowledge Distillation