Awesome AI Agents
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Sahar Abdelnabi — most-cited papers & profile · AI Agents
← authors
·
overview
Sahar Abdelnabi
11
papers ·
44
citations ·
8
h-index
University of Massachusetts Amherst · Max Planck Institute for Intelligent Systems · Max Planck Institute for Biology
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
2026
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
2026
Safety Must Precede the Deployment of Open-Ended AI
2025
Top co-authors
Abhinav Kumar
· 1
Eugene Bagdasarian
· 1
Ferdinando Fioretto
· 1
Ivaxi Sheth
· 1
Ivaxi Sheth
· 1
Jan Wehner
· 1
Leonidas Raghav
· 1
Mario Fritz
· 1
Mario Fritz
· 1
Mason Nakamura
· 1
Ruta Binkyte
· 1
Saaduddin Mahmud
· 1
Topics
Multi-Agent
Safety
Evaluation
Memory