Shengbang Tong

PhD student, New York University

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

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

#515 · Junhong Shen, Hao Bai, Lunjun Zhang, Yifei Zhou, Amrith Setlur, Shengbang Tong, Diego Caples, Nan Jiang, Tong Zhang, Ameet Talwalkar, Aviral Kumar

We propose to scale the number of interaction steps for agents as a new axis of test-time scaling and develop a curriculum-based online RL algorithm for training agents to scale interaction.