Amrith Setlur

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning

Learning to Reason on Hard Problems with Privileged On-Policy Exploration

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Optimizing Test-Time Compute via Meta Reinforcement Finetuning

What Do Learning Dynamics Reveal About Generalization in LLM Mathematical Reasoning?

Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction

Scaling Test-Time Compute Without Verification or RL is Suboptimal

Pre-Memorization Train Accuracy Reliably Predicts Generalization in LLM Reasoning