EXTRAAMAS 2026 | Program

Room: APHRODITE B | Web Link | Download the Program

Welcome and Opening Remarks 09:00 — 09:05

Session 1 Foundations & Limits of Explainability in Agent(s/ic) Systems 09:05 — 10:30

Chair: Prof. Davide Calvaresi

09:05–09:35

KeynoteRe-evaluating Responsible AI in the AI-First Age

Rachele Carli

09:35–09:50

Full PaperMaking AI Memory Transparent: Explainability for Persistent State in Agentic Systems

Matthew Stewart

09:50–10:05

Full PaperPredicting the Cost of Explanations in Optimisation Problems

Roger Lera-Leri et al.

10:05–10:20

Full PaperThe Illusion of Explainability with LLMs and LLM-Agents

Sara Montese, Sergio Alvarez-Napagao, Victor Gimenez-Abalos, Ulises Cortés

10:20–10:30

DemoExplainable Agentic Oversight: A Multi-Agent System for Transparent Groundwater Regulatory Decision Support

Ayyub Alzahem et al.

Session 2 Trust, Ethics, and Human-Centred Explainable AI 11:00 — 12:30

Chair: Dr. Rachele Carli & Dr. Amro Najjar

11:00–11:15

Short PaperSocial Dynamics of Trust Formation in XAI Systems: A Multi-Agent Approach

Narendar Kumar et al.

11:15–11:30

Full PaperPerceived Trustworthiness of Large Language Models and Attitudes Toward Them

Muaadh Noman et al.

11:30–11:45

Full PaperAuditing LLM Multi-Agent Systems via Protocolized Interaction Traces

Azzedine Idir Ait Said et al.

11:45–12:00

Full PaperBias Mitigation in Quantum Machine Learning

Alessandro Marchetti et al.

12:00–12:15

Full PaperDesigning a Trustworthy Intelligent Agent for Legal Reasoning

Alessia Donata Camarda et al.

12:15–12:30

Full PaperEmergence of Secondary Norm from Distributed Interaction of Autonomous Agents

Edoardo Zappia et al.

Session 3 Methods for Explainability: Argumentation, Learning, and Hybrid AI 14:00 — 15:30

Chair: Prof. Kary Främling

14:05–14:35

KeynoteHuman-AI Collaboration: From Support to Dependency and What Design Can Do

Prof. Dr. Raian Ali

14:35–14:50

Full PaperArgVLLMs: Structuring Multimodal Reasoning

Tianyi Ma, Francesca Toni, Soteris Demetriou

14:50–15:05

Full PaperTowards Trustworthy Temporal Event Reasoning

Sukriti Bhattacharya et al.

15:05–15:20

Full PaperM2-PALE: Explaining Multi-Agent MCTS–Minimax Hybrids

Yiyu Qian et al.

15:20–15:30

Full PaperCritic-Driven Voronoi-Quantization for Distilling Deep RL Policies

Senne Deproost et al.

Session 4 Systems and Applications of Explainable Multi-Agent Systems 16:00 — 17:45

Chair: Dr. Amro Najjar

16:00–16:15

Full PaperEvolutionary Rule Extraction from Corporate Default Prediction Models

Desiré Fabbretti et al.

16:15–16:30

Full PaperUser-Adapted and Interactive Explainability with Knowledge Graphs

Kary Främling

16:30–16:45

Full PaperTranslation as a Decision Space: A Multi-Agent Perspective

Hasan Alkhder et al.

16:45–17:00

Full PaperRashomon Memory

Albert Sadowski, Jaroslaw A. Chudziak

17:00–17:15

Full PaperTalk2Prolog: from Controlled Natural Language to Prolog

Laura Fuciarelli et al.

17:15–17:30

Full PaperToward Explanatory Equilibrium: Verifiable Reasoning as a Coordination Mechanism under Asymmetric Information

Feliks Bańka and Jaroslaw A. Chudziak

17:30–17:45

Full PaperExploring Vision Features with Sparse Autoencoders

Marlin Lee et al.

Closing Remarks and Thanks 17:45 — 17:50