Miltiadis Stouras

Hello, I'm Miltos! I'm a PhD Student at EPFL's Theory Group where I am advised by Ola Svensson.

I've been working on designing algorithms under uncertainty, including settings like stochastic optimization, online decision-making, and data-driven algorithm design. More recently, I've been exploring applications in adaptive retrieval-augmented generation (RAG), AI for education, and automated design of agentic systems.

In Summer 2026, I was a Research Intern at Google Zürich, where I worked on automated design and recursive self-improvement of agentic harnesses with Reza Shokri and Amir Zandieh.

Before joining EPFL, I did my undergraduate studies at the National Technical University of Athens, where I completed my master's thesis with Dimitris Fotakis. During that time, I co-founded White Noise, the space engineering team of NTUA, and gained some industry experience working as a Software Engineering Intern at Amazon.

PhD Student

EPFL, Switzerland

miltiadis.stouras@epfl.ch

Publications

(α-β) indicates alphabetical author ordering

^(α-β) Space-Efficient Language Generation in the Limit

Nicolas Flammarion, Chirag Pabbaraju, Hristo Papazov, Miltiadis Stouras, Ola Svensson

COLT 2026

arXiv
Retriever Portfolios: A Principled Approach to Adaptive RAG

Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi, Ola Svensson

ICML 2026

arXiv code poster
^(α-β) An Optimal Algorithm for Stochastic Vertex Cover

Jan van den Brand, Inge Li Gørtz, Chirag Pabbaraju, Debmalya Panigrahi, Cliff Stein, Miltiadis Stouras, Ola Svensson, Ali Vakilian

STOC 2026

arXiv
Online Two-Stage Submodular Maximization

Iasonas Nikolaou, Miltiadis Stouras, Stratis Ioannidis, Evimaria Terzi

NeurIPS 2025

arXiv
^(α-β) Data-Driven Solution Portfolios

Marina Drygala, Silvio Lattanzi, Andreas Maggiori, Miltiadis Stouras, Ola Svensson, Sergei Vassilvitskii

ITCS 2025

arXiv video
^(α-β) Graph Connectivity with Noisy Queries

Dimitris Fotakis, Evangelia Gergatsouli, Charilaos Pipis, Miltiadis Stouras, Christos Tzamos

MFCS 2023

arXiv

Publications in Education

Turning 500+ Students into Teachers: A Semester-Long Study of an AI Teachable Agent in an Undergraduate Algorithms Course

Chenyang Wang, Amaury George, Miltiadis Stouras, Christopher Grant Petrie, Nicolas Ettlin, Paola Mejia-Domenzain, Vinitra Swamy, Tanja Käser, Ola Svensson

ACM Learning at Scale 2026
Taking School Instrumentation One Step Forward: A Do-It-Yourself Type Spectrophotometer and a Jupyter Notebook That Enable Real Time Spectroscopy during School Lessons

Marianna Fanouria Mitsioni, Miltiadis Stouras, Christodoulos Makedonas

Journal of Chemical Education 2023

Teaching

I'm honored to have received the 2024 Teaching Assistant Award from the CS Department of EPFL.

Algorithms I, EPFL
In Spring 2026, I gave 4 guest lectures on Dynamic Programming and Randomized Algorithms.

Spring 2024, 2025, 2026
Algorithms II, EPFL
Fall 2023, 2024
Theory of Computation, EPFL
Spring 2022
Advanced Algorithms, NTUA
Spring 2021
Algorithms & Complexity, NTUA
Fall 2020
Greek preparation camp for IOI
2019-2022