29 citations · 53 across the 26 of their papers we have counts for
30 papers
Repairing LLM-Generated Specifications with Deterministic Diagnosis
Giovanni Vaccarino, Emanuele La Malfa, Dehai Min +6
Large language models (LLMs) are increasingly used as formalizers: given a reasoning problem expressed in natural language, they produce a formal specification that a symbolic solv…
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
Emanuele La Malfa, Saar Cohen, Gabriele La Malfa +4
Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly use mosaic…
Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios?
Gabriele La Malfa, Nitay Alon, Emanuele La Malfa +2
Theory of Space framework (ToS) assesses the spatial understanding of curiosity-driven Vision-Language Models (VLMs) under partial observability. As AI techniques are increasingly…
The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play
Gabriele La Malfa, Emanuele La Malfa, Saar Cohen +4
Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in a zero-sum game, i.e., where…
Agentic Business Process Management: A Research Manifesto
Diego Calvanese, Angelo Casciani, Giuseppe De Giacomo +15
This paper presents a manifesto that articulates the conceptual foundations of Agentic Business Process Management (APM), an extension of Business Process Management (BPM) for gove…
Benchmarking at the Edge of Comprehension
Samuele Marro, Jialin Yu, Emanuele La Malfa +8
As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improv…
Tacit Coordination of Large Language Models
Ido Aharon, Emanuele La Malfa, Michael Wooldridge +1
Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require coordination without communication, from human-AI interaction to safety-critical scenari…
End-to-end PDDL Planning with Hardcoded and Dynamic Agents
Emanuele La Malfa, Ping Zhu, Samuele Marro +2
We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Plan…
Fetch.ai: An Architecture for Modern Multi-Agent Systems
Michael J. Wooldridge, Attila Bagoly, Jonathan J. Ward +2
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such…
Large Language Models Miss the Multi-Agent Mark
Emanuele La Malfa, Gabriele La Malfa, Samuele Marro +5
Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of t…
Fixed Point Explainability
Emanuele La Malfa, Jon Vadillo, Marco Molinari +1
This paper introduces a formal notion of fixed point explanations, inspired by the "why regress" principle, to assess, through recursive applications, the stability of the interpla…
Language Models Are Implicitly Continuous
Samuele Marro, Davide Evangelista, X. Angelo Huang +3
Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function ap…
Out-of-Context Reasoning in Large Language Models
Jonathan Shaki, Emanuele La Malfa, Michael Wooldridge +1
We study how large language models (LLMs) reason about memorized knowledge through simple binary relations such as equality (), inequality (), and inclusion (). Unli…
When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits
Jabez Magomere, Emanuele La Malfa, Manuel Tonneau +2
Online misinformation remains a critical challenge, and fact-checkers increasingly rely on claim matching systems that use sentence embedding models to retrieve relevant fact-check…
Code Simulation as a Proxy for High-order Tasks in Large Language Models
Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +6
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We coll…
Jailbreaking Large Language Models in Infinitely Many Ways
Oliver Goldstein, Emanuele La Malfa, Felix Drinkall +2
We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded commu…
A Scalable Communication Protocol for Networks of Large Language Models
Samuele Marro, Emanuele La Malfa, Jesse Wright +4
Communication is a prerequisite for collaboration. When scaling networks of AI-powered agents, communication must be versatile, efficient, and portable. These requisites, which we…
Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks
Fangru Lin, Shaoguang Mao, Emanuele La Malfa +7
Language is not monolithic. While benchmarks, including those designed for multiple languages, are often used as proxies to evaluate the performance of Large Language Models (LLMs)…
A Notion of Complexity for Theory of Mind via Discrete World Models
X. Angelo Huang, Emanuele La Malfa, Samuele Marro +3
Theory of Mind (ToM) can be used to assess the capabilities of Large Language Models (LLMs) in complex scenarios where social reasoning is required. While the research community ha…
Deep Neural Networks via Complex Network Theory: a Perspective
Emanuele La Malfa, Gabriele La Malfa, Giuseppe Nicosia +1
Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging stat…
Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
Fangru Lin, Emanuele La Malfa, Valentin Hofmann +3
Planning is a fundamental property of human intelligence. Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time cost…
Code Simulation Challenges for Large Language Models
Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +5
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. This wo…
Language Models as a Service: Overview of a New Paradigm and its Challenges
Emanuele La Malfa, Aleksandar Petrov, Simon Frieder +6
Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the Languag…
Language Model Tokenizers Introduce Unfairness Between Languages
Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr +1
Recent language models have shown impressive multilingual performance, even when not explicitly trained for it. Despite this, there are concerns about the quality of their outputs…