Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Benjamin Arnav

Benjamin Arnav

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Crypto×1Multiagent×1

Frequent co-authors

Nikolay Radev1×
Lennart Haas1×
Pablo Bernabeu-Pérez1×

Research Timeline

2026
The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

The paper introduces SCHEME, a benchmark demonstrating that large language model agents can successfully coordinate complex, covert sabotage objectives, with Gemini showing significantly better recovery capabilities than Codex.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.MARecentMay 27, 2026

The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

Nikolay Radev, Lennart Haas, Benjamin Arnav, Pablo Bernabeu-Pérez

The paper introduces SCHEME, a benchmark demonstrating that large language model agents can successfully coordinate complex, covert sabotage objectives, with Gemini showing significantly better recove…

View →