Agent AI is one of the important research directions after we had significant success with multimodal large language models. It leads to the chance of using AI for business analysis, and also increases the uncertainty in scenario planning. 

Scenario planning finds its most potent applications in fields rife with uncertainty. Long-term strategic planning, geopolitics, and nascent industries are arenas where the linearity of traditional forecasting proves inadequate. While scenario planning isn't novel, its confluence with modern technological tools like NLP brings forth exciting prospects. With the rise of generative NLP technologies, as highlighted by recent research, there's an evolving landscape where scenario planning can be further refined, automated, and diversified. NLP's capability to parse vast textual datasets, identify emerging patterns, and even generate detailed narratives makes it a formidable tool in the scenario planner's toolkit.

The modern era, with its rapid technological advancements, geopolitical flux, and ever-changing socio-economic landscapes, encapsulates the VUCA paradigm - Volatile, Uncertain, Complex, and Ambiguous. Within this framework, traditional predictive methodologies, which often rest on linear extrapolations of existing trends, fall short. Unlike predictive models that seek precision based on historical and current data, scenario planning delves into a different realm. It doesn't merely project an extrapolated future; it crafts multiple narratives, each shedding light on a potential future. Rather than trying to predict a single path forward, scenario planning embraces the multifaceted, uncertain nature of the future. It takes into account various driving forces and uncertainties, crafting stories that present alternative futures, some of which may even seem improbable. This approach isn't about predicting the right future but about being prepared for a spectrum of possibilities. 

Following this line of thought, the aim of AgentScen workshop is to discuss the potential of agent AI for scenario planning. For example, Scenario planning can be applied to key healthcare and biomedical domains, including pandemic preparedness, hospital resource management, medical technology advancements, health insurance sustainability, and the future of telemedicine. By integrating qualitative and quantitative approaches—ranging from expert-driven scenario narratives to data-driven modeling—participants will learn how to navigate uncertainty and proactively shape the future of healthcare. Additionally, in finance and business fields, scenario planning can help executives, financial analysts, and decision-makers navigate uncertainty in areas such as market volatility, interest rate fluctuations, investment risks, corporate financial planning, regulatory changes, and technological disruptions. By constructing and analyzing alternative scenarios, organizations can better anticipate potential challenges and capitalize on emerging opportunities.

Submission Guidelines

• Deadline for Paper Submissions: May 9, 2025 - Submission Site: https://easychair.org/my/conference?conf=agentscen2025

• Notification of Acceptance: June 6, 2025

• The ACL Template MUST be used for your submission(s). Accepted papers proceedings will be published at ACL Anthology. 

• Long Paper:  May consist of up to 8 pages of content, plus unlimited pages for references and appendix. 

• Short Paper and Demo Paper: May consist of up to 4 pages of content, plus unlimited references and appendix.

List of Topics

We invite submissions of research papers on all topics related to agent AI for scenario planning in terms of both full papers and short papers for either oral or poster presentation. Original studies reporting joint work are therefore especially encouraged.

Topics of interest include, but are not limited to:

•  Historical and contemporary perspectives on scenario planning

•  Comparative analysis of qualitative vs. quantitative scenario planning methods

•  Advances in computational modeling for scenario planning

•  Integrating probabilistic forecasting with scenario planning

•  Artificial Intelligence and Generative Models in Scenario Planning

•  Large Language Models for automated scenario narratives

•  Multi-agent systems for interactive and dynamic scenario simulation

•  Reinforcement learning and adaptive AI in scenario generation

•  AI-driven uncertainty analysis in business and finance scenarios

•  Ethics, Bias, and Governance in AI-Driven Scenario Planning

•  Addressing algorithmic biases in AI-generated scenarios

•  Transparency and explainability in AI-generated strategic foresight

•  Governance frameworks for AI-driven decision support systems

•  Explainable and interpretable AI in strategic planning

•  Multi-agent simulations for complex decision-making

•  Emerging AI techniques for scenario-based policy modeling

•  Real-World Applications and Case Studies

•  Industry case studies of agent AI in scenario planning

Organizing Committee

• Chung-Chi Chen - Artificial Intelligence Research Center, AIST, Japan

• Tatsuya Ishigaki - Artificial Intelligence Research Center, AIST, Japan

• Sophia Ananiadou - University of Manchester, UK

• Hiroya Takamura - Artificial Intelligence Research Center, AIST, Japan

Contact

All questions about submissions should be emailed to c.c.chen@acm.org