Rishabh Agarwal

Adjunct Professor, Computer Science, McGill University

Joined

February 2019

Names

Rishabh Agarwal (Preferred)

Emails

****@gmail.com (Confirmed)

****@google.com (Confirmed)

****@mila.quebec (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Adjunct Professor

Computer Science, McGill University (mcgill.ca)

2024 – Present

Researcher

Facebook (meta.com)

2025 – 2025

Research Scientist

Google DeepMind (google.com)

2018 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Aaron Courville

Present

PhD Advisor

Marc Bellemare

Present

Expertise

Deep Reinforcement Learning

Present

Publications

Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville
- SPOT
- Readers: Everyone
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville
- ICLR 2026 Workshop DATA-FM
- Readers: Everyone
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, Lu Wang
- Accepted by TMLR
- Readers: Everyone
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran, Jaekyeom Kim, Hao Peng, Moontae Lee, Honglak Lee, Lu Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Shape of Thought: When Distribution Can Matter More than Correctness in Reasoning Tasks
Abhranil Chandra, Ayush Agrawal, Arian Hosseini, Sebastian Fischmeister, Rishabh Agarwal, Navin Goyal, Aaron Courville
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
The Art of Scaling Reinforcement Learning Compute for LLMs
Fnu Devvrit, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Sai Surya Duvvuri, Manzil Zaheer, Inderjit S Dhillon, David Brandfonbrener, Rishabh Agarwal
- ICLR 2026 Oral
- Readers: Everyone
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Kusha Sareen, Morgane M Moss, Alessandro Sordoni, Rishabh Agarwal, Arian Hosseini
- AI4Math@ICML25 Poster
- Readers: Everyone
Towards Compute-Optimal Many-Shot In-Context Learning
Shahriar Golchin, Yanfei Chen, Rujun Han, Manan Gandhi, Tianli Yu, Swaroop Mishra, Mihai Surdeanu, Rishabh Agarwal, Chen-Yu Lee, Tomas Pfister
- COLM 2025
- Readers: Everyone
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Kusha Sareen, Morgane M Moss, Alessandro Sordoni, Arian Hosseini, Rishabh Agarwal
- COLM 2025
- Readers: Everyone

View all 75 publications

Co-Authors

View all 223 co-authors