Joint Workflow and Prompt Optimization for User Behavior Simulation
SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts.
ProofPaper ↗
Key points
- User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users.
- It supports system testing and evaluation, decision-making and forecasting, and user experience design.
- The experimental results demonstrate that SWORD achieves statistically significant gains over prompt-only, workflow-only, and staged-optimization baselines under a controlled, identical-backbone comparison.
- Beyond predictive performance, SWORD autonomously discovers domain-relevant signals, review-sentiment mapping rules and epidemiological decay priors, purely from scalar error feedback, establishing textual gradients as a mechanism for unsupervised feature-importance discovery in user behavior modeling.
Sources (1)
- [1]Joint Workflow and Prompt Optimization for User Behavior SimulationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 02:59 AM
SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts.
User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users.
Extractive summary: sentences quoted from the sources.