# Joint Workflow and Prompt Optimization for User Behavior Simulation

arXiv: https://arxiv.org/abs/2610.07663 · HTML: https://mlsanity.com/paper/2610.07663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 75 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction](https://mlsanity.com/paper/2305.06474/) (2023)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization](https://mlsanity.com/paper/2502.04306/) (2025)
- [EvoFlow: Evolving Diverse Agentic Workflows On The Fly](https://mlsanity.com/paper/2502.07373/) (2025)
- [SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users](https://mlsanity.com/paper/2504.10157/) (2025)
- [From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning](https://mlsanity.com/paper/2411.03817/) (2024)
- [Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline](https://mlsanity.com/paper/2601.12307/) (2026)
- [LLM-AutoDiff: Auto-Differentiate Any LLM Workflow](https://mlsanity.com/paper/2501.16673/) (2025)
- [SEW: Self-Evolving Agentic Workflows for Automated Code Generation](https://mlsanity.com/paper/2505.18646/) (2025)
- [RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents](https://mlsanity.com/paper/2406.11132/) (2024)
- [From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation](https://mlsanity.com/paper/2507.19364/) (2025)
- [Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization](https://mlsanity.com/paper/2410.19499/) (2024)
- [MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks](https://mlsanity.com/paper/2603.02630/) (2026)
- [MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.06623/) (2026)
- [Universal Masking is Urgent in the COVID-19 Pandemic: SEIR and Agent Based Models, Empirical Validation, Policy Recommendations](https://mlsanity.com/paper/2004.13553/) (2020)
- [BESSIE: A Behavior and Epidemic Simulator for Use With Synthetic Populations](https://mlsanity.com/paper/2203.11414/) (2022)
- [Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation](https://mlsanity.com/paper/2507.09839/) (2025)

## Abstract (arXiv)

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. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. 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. It is guided solely by a scalar task metric, without domain initialization or task-specific engineering. 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. Against the strongest published domain-specific baseline, SWORD further improves accuracy while using a smaller backbone model, substantially less training data, and a very reasonable API cost (4--6 for each dataset). 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.