Explore projects

This project explores the potential of Generative Autonomous Agents and Multiagent Systems (GAAMAS) for social simulation. It aims to better understand how these artificial entities, powered by Large Language Models (LLMs), interact, make decisions, adapt to others' behaviour, and simulate human reasoning, particularly in strategic contexts inspired by Game Theory. This project will contribute to assessing the current capabilities and limitations of GAAMAS and to proposing concrete avenues for improving their coherence and realism in social simulations.

Workflow provenance consolidation and querying in Neo4j and OpenSearch

Python Generative Autonomous Agents and Multi-Agent Systems aims to evaluate the social behaviors of LLM-based agents.

This repository contains a collection of papers and ressources related to generative AAMAS.

An extension of the PyMARL codebase that includes additional algorithms and environment support

AVSS 2026 Paper titled:

"Diffusion-Based Multi-Class Normality for OOD Detection: An Application to CDP Authentication"

In this work, we propose a multi-class normality approach based on diffusion models for out-of-distribution (OOD) detection and apply it to copy detection pattern (CDP) authentication. We consider authentic copy detection patterns as in-distribution classes and counterfeit patterns as out-of-distribution samples, and compute a reconstruction-based signal by masking regions of the input and comparing them with their corresponding reconstructions generated by a conditioned diffusion model.