Evil Geniuses: Delving into the Safety of LLM-based Agents.
Yu TianXiao YangJingyuan ZhangYinpeng DongHang SuPublished in: CoRR (2023)
Keyphrases
- multi agent systems
- multi agent
- multiagent systems
- intelligent agents
- software agents
- multiple agents
- cooperative
- learning agents
- resource bounded
- autonomous agents
- mobile agents
- incomplete information
- artificial agents
- coalition formation
- agent systems
- agent model
- agent technology
- complex environments
- dynamic environments
- multi agent planning
- agent cooperation
- distributed agents
- interacting agents
- bounded rationality
- heterogeneous agents
- social welfare
- logical framework
- action selection
- decision theoretic