R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.
Tongxin YuanZhiwei HeLingzhong DongYiming WangRuijie ZhaoTian XiaLizhen XuBinglin ZhouFangqi LiZhuosheng ZhangRui WangGongshen LiuPublished in: CoRR (2024)
Keyphrases
- multi agent
- multi agent systems
- decision making
- multiple agents
- multiagent systems
- intelligent agents
- autonomous agents
- resource allocation
- software agents
- risk averse
- cooperative
- artificial agents
- agent architecture
- risk management
- mobile agents
- agent systems
- action selection
- learning agents
- single agent
- risk assessment
- agent model
- neural network
- incomplete information
- decision theoretic
- risk factors
- high risk
- reasoning process
- combinatorial auctions
- agent interactions
- agent based models
- agent technology
- safety critical
- dynamic environments
- risk measures
- distributed agents