Scholar
Andi Peng
Google Scholar ID: S63gb38AAAAJ
Research Scientist, Anthropic
reward learning
reinforcement learning
safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,395
H-index
13
i10-index
16
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
4 items
Human-Guided Harm Recovery for Computer Use Agents
2026
Cited
0
Task Completion Agents are Not Ideal Collaborators
2025
Cited
0
Stress-Testing Model Specs Reveals Character Differences among Language Models
2025
Cited
0
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Neural Information Processing Systems · 2024
Cited
1
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
×
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