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.

Create and manipulate RO-Crate and Provenance Run RO-Crate metadata for workflows. Generate RO-Crate metadata files for CWL workflows.

A small python script to extract annotations from vivlio e-reader

Workflow provenance consolidation and querying in Neo4j and OpenSearch

Financed by the ASLAN LabEx, a wrapper around wiktextract for live querying.

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

This repository provides all the scripts and tools developed to automatically build a geo-historical knowledge graph from articles of the Encyclopédie of Diderot and d’Alembert (EDdA).