Get started
Author

Matteo Prandi

Observed names: Prandi, M., Prandi, Matteo
Observed institution: Sapienza University of Rome
OpenAlex ID: A5123089628
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
2026 · Syrnikov, Marcantonio Bracale, Pierucci, Federico, et al. · arXiv (Cornell University) · 34
PDF
Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
2025 · Bisconti, Piercosma, Galisai, Marcello, et al. · arXiv (Cornell University) · 17
PDF
Institutional AI: A Governance Framework for Distributional AGI Safety
2026 · Pierucci, Federico, Galisai, Marcello, et al. · arXiv (Cornell University) · 14
PDF
Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
2025 · Prandi, Matteo, Suriani, Vincenzo, et al. · arXiv (Cornell University) · 7
PDF
From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
2025 · Bisconti, Piercosma, Galisai, Marcello, et al. · arXiv (Cornell University) · 4
PDF
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
2026 · Galisai, Marcello, Cifani, Susanna, et al. · arXiv (Cornell University) · 3
PDF
Agentic Microphysics: A Manifesto for Generative AI Safety
2026 · Pierucci, Federico, Prandi, Matteo, et al. · arXiv (Cornell University) · 3
PDF
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
2026 · Bisconti, Piercosma, Prandi, Matteo, et al. · arXiv (Cornell University) · 2
PDF
Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
2026 · Syrnikov, Marcantonio Bracale, Pierucci, Federico, et al. · arXiv (Cornell University) · 1
PDF
Xeno-Interpretability: Investigating the Alien Minds of LLMs
2026 · Pierucci, F., Syrnikov, M. Bracale, et al. · arXiv (Cornell University)
PDF
Metaphor Is Not All Attention Needs
2026 · Sorokoletova, Olga, Giarrusso, Francesco, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 85
H-index: 4
I10-index: 3
Year
Topic
Type