Multi-Agent Personalized Dialogue System
by 凯华 倪
Approaches
Five agents for personalized dialogue generation
Motivation
1. Data scarcity and generalization issues
2. Need for more engaging and authentic interactions
Multi-aspect optimization
Architecture of MAPDS In CPDC
Performance on CPDC dataset with different structure
Agent | Input | Output |
1 . IIA | Profile | Persona |
2 . DHA | Dialogue history | History summary |
3 . DGA | 1, 2 | Dialogue |
Agent | Input | Output |
1 . IIA | Profile, Dialogue history | Persona, Language style, Emotional state |
2 . DHA | Dialogue history | History summary |
3 . DGA | 1, 2 | Dialogue |
Agent | Input | Output |
1 . IIA | Profile, Dialogue history | Persona, Language style, Emotional state |
2 . DHA | Dialogue history | History summary, Topic transitions, Current topic |
3 . DGA | 1, 2 | Dialogue |
Agent | Input | Output |
1 . IIA | Profile, Dialogue history | Persona, Language style, Emotional state |
2 . DHA | Dialogue history | History summary, Topic transitions, Current topic |
3. TPA | 1, 2 | Planned topic |
4 . DGA | 1, 2, 3 | Dialogue |
Agent | Input | Output |
1 . IIA | Profile, Dialogue history | Persona, Language style, Emotional state |
2 . DHA | Dialogue history | History summary, Topic transitions, Current topic |
3. TPA | 1, 2 | Planned topic |
4 . DGA | 1, 2, 3, 5 | Dialogue |
5 . FAA | Profile, Dialogue history, 4 | Feedback |
Structure 1 -- 2.12
Structure 2 -- 2.73
Structure 3 -- 3.54
Structure 4 -- 4.06
Structure 5 -- 4.35