cv

DPhil in Autonomous Intelligent Machines and Systems

University of Oxford

• 4-year DPhil at the Oxford AIMS CDT under Prof. Philip Torr on multi-agent LLMs.
• Funded by a 250k USD Microsoft studentship.

MSc Artificial Intelligence

University of Bologna

• GPA: 29.75/30, top of the class (170 students). Graduation grade: 110 cum laude.

Excellency Degree

Superior College of Bologna (Institute of Superior Studies)

• 7 STEM students are admitted each year and are provided with a personal tutor, exemption from tuition fees, free accommodation and an annual scholarship throughout their Bachelor's and Master's degrees.
• Yearly requirements: 28/30 GPA, no grade lower than 24/30, must take 6 additional excellency courses.
• GPA: 29.88/30

BSc Computer Science

University of Bologna

• GPA: 29.77/30, top of the class (150 students). Graduation grade: 110 cum laude.

• Samuele Marro, Jialin Yu, Emanuele La Malfa, et al., Benchmarking at the Edge of Comprehension. ICML 2026 Oral.

• Emanuele La Malfa, Gabriele La Malfa, Samuele Marro, et al., Large Language Models Miss the Multi-Agent Mark. NeurIPS 2025 Oral.

• Samuele Marro, Emanuele La Malfa, Jesse Wright, Guohao Li, Nigel Shadbolt, Michael Wooldridge, Philip Torr, A Scalable Communication Protocol for Networks of Large Language Models.

• Tobin South, Samuele Marro, Thomas Hardjono, Robert Mahari, Cedric Deslandes Whitney, Dazza Greenwood, Alan Chan, Alex Pentland, Authenticated Delegation and Authorized AI Agents. ICML 2025 Oral.

• Samuele Marro, Davide Evangelista, Angelo Huang, Emanuele La Malfa, Michele Lombardi, Michael Wooldridge. Language Models Are Implicitly Continuous. ICLR 2025.

• Samuele Marro, Michele Lombardi. Computational Asymmetries in Robust Classification. ICML 2023

Head

Institute for Decentralized AI

• Research institute focused on security and infrastructure for decentralized and distributed AI systems.
• Two main units: Oxford and Stanford.
• Funded by a 500k USD grant jointly funded by Google, Anthropic, Microsoft, and OpenAI.

PhD Research Intern

Microsoft

• PhD internship in Microsoft's Agents Team of the Applied Sciences Group.
• Main focus on developing efficient local agents.

Fellow

Cosmos Institute

• Research fellow on the intersection of AI, philosophy, and decentralization.
• Building stable non-governmental institutions to steer AI towards a less authoritarian future.

Predoctoral Research Fellow

University of Bologna

• Department fellowship on adversarial robustness under prof. Michele Lombardi.

Visitor

Oxford University

• Research visit to the Department of Computer Science to conduct research on the Theory of Mind of LLMs under Dr. Emanuele La Malfa and Prof. Michael Wooldridge.

Student Researcher

University of Bologna

• Developed, under prof. Michele Lombardi and Michela Milano, an adversarial defense (implemented in Python + PyTorch) which is robust against white-box attacks.
• Wrote a Julia interface to formally verify the effectiveness of the defense using MIPVerify.jl + Gurobi.
• Proved that training a robust ReLU model is Sigma2P-hard, with implications for adversarial defense design.
• Obtained a 170k core-hour grant for the CINECA supercomputer cluster.

Teaching Assistant

University of Bologna

• Taught the applied ML module of "Introduction to Machine Learning" for the Fall '22 semester.
• Performed research on the latent space of diffusion models under prof. Andrea Asperti.

Research Intern

MindIt Srl + Kantar

• Developed a Tensorflow LSTM implementation compatible with IBM CPLEX optimization algorithms.
• Introduced tools to mitigate numerical issues with non-linear components of LSTMs.
• Rewrote Meta's FBProphet time series model in Tensorflow.

AI Safety Fund Grant, 500k USD

• Grant by the AI Safety Fund, jointly funded by Google, Anthropic, Microsoft, and OpenAI, on decentralized oversight of agent networks.

Cosmos Institution Building Fellowship

• Fellowship by the Cosmos Institute to build new institutions for decentralized AI.

Microsoft Studentship, 250k USD

• Studentship for research into communication protocols between LLMs and multimodal memory in generative models.

CINECA HPC Grant

• Grant for the Galileo100 HPC cluster for research on the computational complexity of adversarial attacks.

• Samuele Marro, Alan Chan, Xinxing Ren, et al., Permission Manifests for Web Agents. Under review at FAccT 2026.

• X Angelo Huang, Emanuele La Malfa, Samuele Marro, et al., A notion of complexity for theory of mind via discrete world models. EMNLP 2024.

• Andrea Asperti, Davide Evangelista, Samuele Marro, et al., Image embedding for denoising generative models. Artificial Intelligence Review.

Decentralized Oversight of Agent Networks

• Presented at the ERA Technical AI Governance Forum.

Agora: A Scalable Protocol for Decentralized Agent Communication

• Presented at Microsoft Ltd (2024) and Camel AI (2025).

The Case for Decentralized Intelligence

• Presented at the Oxford Maths Institute.

Computational Asymmetries in Robust Classification

• Leonardo Lesmo Award talk at AIxIA 2023.

Practical Machine Learning

• Presented at the University of Bologna Algo-UniBo organization.

Solidity Developer and Auditor

Freelance

• Performed Smart Contract audits, Web3 integrations and secure Smart Contract development.
• Specialized in EVM and EVM-like (e.g. Vite) security standards.

Tutor

Liceo Scientifico L. Cocito, Alba (Italy)

• Provided one-on-one and one-on-two tutorship for students struggling with Mathematics and Physics.

Independent Research

• Extended Grammatical Evolution's Backus-Naur Forms to support runtime checks and automatic correction of invalid production rules.
• Implemented this variant of Grammatical Evolution in C# and Python.

Intern

Sistemi Tre, Alba (Italy)

• Automated database queries through the in-house software interface using AHK, leading to a 3-4x increase in data retrieval speed.
• Assisted IT staff during on-site technical support.

ARIA Exploration Grant, 20k GBP

• Exploratory grant on automated protocol design as a path to full cybersecurity resilience.
• Part of the "Trust Everything Everywhere" research area.

AIxIA "Leonardo Lesmo" Award

• Award for the best MSc thesis in AI in Italy, granted by the Italian Association for Artificial Intelligence.

Gitcoin Round 13 Hackathon, 6k USD bounty

• Wrote four smart contracts in Soliditypp for the Vite blockchain.
• Wrote unit tests for such contracts using Vuilder and Javascript.

GreenNFT Hackathon, 3k USD bounty

• Created a model to estimate the environmental impact of individual transactions on Ethereum.
• Identified techniques to reduce a user's individual impact by 70% with the help of Python scripts.
• Developed Green NFT Helper, a JavaScript + Svelte.js website to help users to reduce their emissions.

Gitcoin Round 9 Hackathon, 1k USD bounty

• Developed a Chrome extension in JavaScript to search on IPFS directly from the omnibox.

Ancalau Award, 3k EUR award

• Trained in Python + Tensorflow a CNN to identify illegal dumping locations from aerial data.
• Deployed the model as part of an Android app (written in Java) to capture aerial data and relay landfill locations in real time to a quadcopter.

Mentor

Cambridge ERA Fellowship

• Mentoring fellows on applications of multi-agent security techniques to AI safety.

Chair

Lightweight Agent Standards Working Group

• Industry-academia joint working group focused on standards for agent interactions.
• Notable organizations: Oxford University, Stanford University, MIT, Firecrawl.

Head

Computer Science Student Commission, Superior College of Bologna (ISS)

• Supervised CS student projects and advised students on CS and ML-related research directions.

Representative

CS Department, University of Bologna

• Managed student-department relations and represented student interests in department meetings.