Workshop Introduction

Causality, Agents and Large Models (CALM) represents three rapidly-growing fields within artificial intelligence research. This workshop aims to bridge the gap between these disciplines by investigating how causal reasoning can enhance the capabilities of multi-agent systems (MAS). The workshop will provide a forum for researchers to discuss theoretical foundations, practical applications, and future directions at the intersection of causal AI, Large Language Models (LLM) and MAS.

Workshop goals:

• Explore the role of causal reasoning in enhancing decision-making, coordination, and adaptation in multi-agent systems. 
• Discuss technical challenges and opportunities for integrating causal AI techniques with Large Models and MAS frameworks.
• Foster interdisciplinary collaboration between researchers in the fields of causal reasoning, Pre-trained Large Models, and MAS.
• Identify promising directions for future research and development in this emerging area.

Submission Guidelines

Submissions will be reviewed by at least three members of the program committee, who are experts in the field. The acceptance of the submitted papers will depend on their quality, relevance, and originality. 

Participants are therefore invited to submit the following two types of papers:

• Long papers: up to 16 pages in length (incl. references)
• Short papers: up to 5 pages in length (incl. references)

Papers must be edited using the LNCS format (applying the LNCS post-proceedings template) and have to be submitted electronically as PDF files via the EasyChair submission page:  TBD

All papers will be subject to double-blind review.

Important Dates

• Submission deadline: October 01th, 2025
• Notification: October 24th, 2025
• Final date for camera-ready copy: TBD
• Workshop: December 03rd, 2025

List of Topics

• Theoretical foundations of causal reasoning in Multi-Agent Systems (MAS)
• Causal reasoning capabilities in Large Models (e.g., Large Language Models, LLMs)
• Theoretical and practical Agentic-AI
• Applications of causal AI techniques in agent-based modeling and simulation
• Causal inference in complex and dynamic multi-agent environments
• Mechanistic Interpretability of Causality in Large Language Models
• Integration of causal reasoning with decision-making and planning in MAS
• Learning causal models from observational and interventional data in MAS
• Causal reasoning for coordination, cooperation, and communication among agents
• Challenges and opportunities for incorporating causal AI into MAS frameworks
• Case studies and empirical evaluations of causal AI approaches in agents
• Generative AI as preprocessing for MAS
• Exploring causality with deep generative models
• Digital twins and simulators for interpretable synthetic data generation
• Graph neural network causal learning
• Causal reinforcement learning
• Interpretable/Explainable root cause analysis methods
• Explainable AI with active inference techniques
• Logic and argumentation-based approaches to causal reasoning

Committees

Workshop Chairs

• Dr. Yazan Mualla (Belfort-Montbeliard University of Technology, France). yazan.mualla[at]utbm.fr
• Dr. Liuwen Yu (University of Luxembourg, Luxembourg). liuwen.yu[at]uni.lu
• Dr. Hui Zhao (Tongji University, China). huizhao[at]tongji.edu.cn
• Dr. Amro Najjar (Luxembourg Institute of Science and Technology, Luxembourg). amro.najjar[at]list.lu

Advisory Board

• Prof. Dr. Stéphane Galland (Belfort-Montbeliard University of Technology, France)
• Prof. Dr. Abdeljalil Abbas-Turki (Belfort-Montbeliard University of Technology, France)

Program Committee

• TBA

Publication

All accepted papers will be published in the Springer proceedings Communications in Computer and Information Science (CCIS) series devoted to the publication of proceedings of computer science conferences.

Venue

University of Luxembourg, Luxembourg, 1-4 December 2025.