Causal Analysis and Opinion Dynamics for Safe Multi‑Agent AI Systems - 2026_IDR_DEIB_43

Position: Research appointment (pre-doc) Institute: Polytechnic of Milano
Posted on: 04/06/2026 Deadline: 10/07/2026

Scientific-Disciplinary Group

09/IINF-05 - Information Processing Systems

Description

This program applies causal inference methods and opinion dynamics models to analyze and ensure safety of AI agents in multi‑agent settings. It will study emergent risks (collusion, polarization, error escalation) and intervention mechanisms based on cause‑effect relationships and belief dynamics among agents. Validation through simulation.

Number of positions

1

Funding body

Politecnico di Milano

Selection process

Click to expand
In order to participate in the selection, please read the call ("bando") available at the following website: https://www.polimi.it/en/bandi-incarichidiricerca Relevance and pertinence of the publications, theses and scientific products attached to the research programme covered by the Fellowship (up to 20 points) Relevance and pertinence of previous research activities and work experience, if any, in relation to the research activity covered by the Fellowship (up to 50 points) Relevance and pertinence of their study programme to the research programme covered by the Fellowship (up to 30 points)