Awesome AI Agents
π
Papers
π§
Topics
π₯
Trending
πΊοΈ
Map
π
Leaderboards
π
Learn
π€
Ask AI
β―
More
π₯
Authors
π
Reading Packs
π
Datasets
π οΈ
Tools
π°
News
π
Blogs
βοΈ
Newsletter
π―
Research Radar
π
Saved
+ Add Paper
βΎ
β
β authors
Β·
overview
Loading authorβ¦
π€
Ask AI
David Evans β most-cited papers & profile Β· AI Agents
β authors
Β·
overview
David Evans
10
papers Β·
335
citations Β·
0
h-index
Google Scholar β
Semantic Scholar β
OpenAlex β
Most-cited papers
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
2026
Top co-authors
Matjaz Gams
Β· 1
Satish Mahadevan Srinivasan
Β· 1
Zelalem Abahana
Β· 1
Topics
Evaluation
Safety