PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems
Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. Our analysis of 16K real-world sessions shows that 75.9% of interactions are multi-turn, revealing a substantial gap between how users interact with agents and how such systems are trained and evaluated. We introduce \textbf{PersonaForge}, a user simulation framework for synthesizing realistic multi-turn user--agent interactions. PersonaForge combines a four-dimensional persona space, SOUL-driven behavioral control ca
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%CodeForge-15B →
“Fuzzy title match (0.94): “PersonaForge: Realistic Multi-Turn User Simulation for Agent” ≈ “CodeForge-15B””
- FuzzyOverlapping authors or contributors · 62%Kong/kong →
“Shared author/contributor keys: kong”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: luo”
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “PersonaForge: Realistic Multi-Turn User Simulation for Agent” ≈ “Fosowl/agenticSeek””
- FuzzySimilar title/name (fuzzy) · 59%WenyuChiou/awesome-agentic-ai-zh →
“Fuzzy title match (0.73): “PersonaForge: Realistic Multi-Turn User Simulation for Agent” ≈ “WenyuChiou/awesome-agentic-ai-zh””
- LinkedLinked via arxiv author · 85%Hanglong Lv →
“PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems”
- LinkedLinked via arxiv author · 85%Dawei Zhu →
“PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems”