Identifying the Risks of LM Agents with an LM-Emulated Sandbox.
Yangjun RuanHonghua DongAndrew WangSilviu PitisYongchao ZhouJimmy BaYann DuboisChris J. MaddisonTatsunori HashimotoPublished in: ICLR (2024)
Keyphrases
- language model
- language modeling
- multi agent
- multi agent systems
- decision making
- multiagent systems
- autonomous agents
- multiple agents
- cooperative
- cooperative multiagent systems
- software agents
- agent architecture
- intelligent agents
- distributed agents
- resource allocation
- query expansion
- agent model
- tf idf
- distributed constraint optimization problems
- interacting agents
- agent systems
- agent technology
- probabilistic model
- virtual environment
- mobile agents