Research Profile

Francesco Argenziano

PhD student in Artificial Intelligence and Robotics at Sapienza University of Rome, focused on scene understanding, 3D scene graphs, and task planning.

Read the full bio

News

Mar 2026Our new preprint "R2F: Repurposing Ray Frontiers for LLM-free Object Navigation" is available on arXiv 🚀!
Feb 2026Our paper "Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning" has been accepted to ICRA 2026 🎉!
Jan 2026Our paper "LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments" has been accepted to the WACV 2026 SG4SI workshop 🎉!
Oct 2025Our paper "Dynamic Objects Relocalization in Changing Environments with Flow Matching" got nominated as Best Paper Finalist at the Perception and Planning for Mobile Manipulation in Changing Environments Workshop 🏆!
Oct 2025In Hangzhou 🇨🇳 for IROS 2025 🧳!
Sep 2025Our paper "Defining and Monitoring Complex Robot Activities via LLMs and Symbolic Reasoning" to ICTAI 2025 🎉!
Sep 2025Our paper "Object-Centric Agentic Robot Policies" has been accepted to the SPACE in Vision, Language, and Embodied AI Workshop at NeurIPS 2025 🎉!
Sep 2025Our paper "Dynamic Objects Relocalization in Changing Environments with Flow Matching" has been accepted to the Perception and Planning for Mobile Manipulation in Changing Environments Workshop at IROS 2025 🎉!
Jun 2025Ended my Visiting PhD period ✅!
Feb 2025Started my Visiting PhD period at Mila - Quebec AI Institute in Montreal to work with Prof. Liam Paull 🎓!
Oct 2024In Santiago de Compostela 🇪🇸 for ECAI 2024 🧳!
Oct 2024In Abu Dhabi 🇦🇪 for IROS 2024 🧳!
Jul 2024Attending the MRS 2024 Summer School 📚 in Prague 🇨🇿!
Jul 2024In Eindhoven 🇳🇱 for RoboCup 2024 ⚽!
Jul 2024Our papers "Neural reward machines" and "Multi-Agent Planning Using Visual Language Models" have been accepted to ECAI 2024 🎉!
Jun 2024Our paper "EMPOWER: embodied multi-role open-vocabulary planning with online grounding and execution" has been accepted to IROS 2024 🎉!
May 2024Honored to have received the award of top 2% of Graduate Students in Sapienza for the year 2021/2022 🏆!
Jul 2023In Daegu 🇰🇷 for RSS 2023!
Jun 2023Attending the ACDL 2023 Summer School 📚 in Grosseto 🇮🇹!
May 2023Our paper "Enhancing Graph Representation of the Environment through Local and Cloud Computation" has been accepted to the Robot Representations for Scene Understanding, Reasoning and Planning Workshop at RSS 2023 🎉!
May 2023Our paper "Visual reward machines" has been accepted to NeSy 2023 🎉!
Nov 2022In Udine 🇮🇹 for AIxIA 2022 🧳!
Nov 2022Our paper "Knowledge acquisition and completion for long-term human-robot interactions using knowledge graph embedding" has been accepted to AIxIA 2022 🎉!
Nov 2022Start of my PhD journey 🎓!

Publications

R2F: Repurposing Ray Frontiers for LLM-free Object Navigation

arXiv preprint arXiv:2603.08475

Francesco Argenziano; John Mark Alexis Marcelo; Michele Brienza; Abdel Hakim Drid; Emanuele Musumeci; Daniele Nardi; Domenico D. Bloisi; Vincenzo Suriani

Project Paper Code

LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments

Workshop on Scene Graph for Structured Intelligence @ IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026

Sara Micol Ferraina; Michele Brienza; Francesco Argenziano; Emanuele Musumeci; Vincenzo Suriani; Domenico D Bloisi; Daniele Nardi

Project Paper Code

Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action

arXiv preprint arXiv:2509.19571

Sacha Morin; Kumaraditya Gupta; Mahtab Sandhu; Charlie Gauthier; Francesco Argenziano; Kirsty Ellis; Liam Paull

Project Paper Code

Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning

IEEE International Conference on Robotics & Automation (ICRA), 2026

Francesco Argenziano*; Emanuele Musumeci*; Michele Brienza*; Abdel Hakim Drid; Vincenzo Suriani; Daniele Nardi; Domenico D Bloisi

Project Paper Code

Defining and Monitoring Complex Robot Activities via LLMs and Symbolic Reasoning

Oral Presentation

IEEE International Conference on Tools with Artificial Intelligence (ICTAI), 2025

Francesco Argenziano; Elena Umili; Francesco Leotta; Daniele Nardi

Project Paper Code

Dynamic Objects Relocalization in Changing Environments with Flow Matching

Best Paper Finalist

Workshop on Perception and Planning for Mobile Manipulation in Changing Environments @ IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

Francesco Argenziano*; Miguel Saavedra-Ruiz*; Sacha Morin; Daniele Nardi; Liam Paull

Paper Code

Object-Centric Agentic Robot Policies

Poster Presentation

Workshop on Space in Vision, Language, and Embodied AI @ Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

Sacha Morin; Kumaraditya Gupta; Mahtab Sandhu; Charlie Gauthier; Francesco Argenziano; Kirsty Ellis; Liam Paull

Paper

EMPOWER: embodied multi-role open-vocabulary planning with online grounding and execution

Oral Pitch Presentation

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

Francesco Argenziano; Michele Brienza; Vincenzo Suriani; Daniele Nardi; Domenico D Bloisi

Project Paper Code

Multi-Agent Planning Using Visual Language Models

Oral Presentation

European Conference on Artificial Intelligence (ECAI), 2024

Michele Brienza; Francesco Argenziano; Vincenzo Suriani; Domenico D Bloisi; Daniele Nardi

Project Paper Code

Neural reward machines

Oral Presentation

European Conference on Artificial Intelligence (ECAI), 2024

Elena Umili; Francesco Argenziano; Roberto Capobianco

Paper Code

Enhancing Graph Representation of the Environment through Local and Cloud Computation

Workshop on Robot Representations for Scene Understanding, Reasoning and Planning @ Robotics: Science and Systems (RSS), 2023

Francesco Argenziano; Vincenzo Suriani; Daniele Nardi

Paper

Visual reward machines

International Workshop on Neural-Symbolic Learning and Reasoning (NeSy), 2023

Elena Umili; Francesco Argenziano; Aymeric Barbin; Roberto Capobianco

Paper Code

Knowledge acquisition and completion for long-term human-robot interactions using knowledge graph embedding

Oral Presentation

International Conference of the Italian Association for Artificial Intelligence (AIxIA), 2022

Francesco Argenziano*; Ermanno Bartoli*; Vincenzo Suriani; Daniele Nardi

Paper