Nikolay Radev
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1Multiagent×1
Frequent co-authors
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