Scholar
Louis Castricato
Google Scholar ID: WrUnrz4AAAAJ
CEO Wayfarer Labs
Reinforcement Learning
RLHF
LLMs
AI Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,379
H-index
15
i10-index
18
Publications
20
Co-authors
15
list available
Contact
Email
louis_castricato@brown.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
COMBAT: Conditional World Models for Behavioral Agent Training
2026
Cited
0
Results of the NeurIPS 2023 Neural MMO Competition on Multi-task Reinforcement Learning
2025
Cited
0
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
2025
Cited
0
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
2025
Cited
0
Resume (English only)
Research Experience
Previously a research scientist at EleutherAI; Co-founder and Team Lead of CarperAI, one of the largest open source RLHF groups.
Education
PhD student at Brown University, studying RLHF Mechanistic Interpretability.
Background
Interests range from computational narratology to reinforcement learning to interpretability.
Miscellany
Contact: louis_castricato@brown.edu
Co-authors
15 total
Stella Biderman
EleutherAI
Edward Raff
CrowdStrike, UMBC
Co-author 3
Spencer Frazier
PhD Candidate, Georgia Tech
Shahbuland Matiana
Undergraduate Data Science, University of Waterloo
Mark Riedl
Professor of Computing, Georgia Institute of Technology
Co-author 7
Jonathan C Balloch
Georgia Institute of Technology
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up