Aligning LLM Agents by Learning Latent Preference from User Edits.
Ge GaoAlexey TaymanovEduardo SalinasPaul MineiroDipendra MisraPublished in: CoRR (2024)
Keyphrases
- learning systems
- user interaction
- learning algorithm
- action selection
- multi agent
- learning process
- prior knowledge
- online learning
- learning agents
- multi agent systems
- multiagent systems
- end users
- user preferences
- multiagent learning
- probabilistic model
- reinforcement learning
- collaborative filtering
- supervised learning
- active learning
- software agents
- decision theoretic
- learning capabilities
- discriminative learning
- learned knowledge
- e learning
- decision making