Author name cluster

Bruno Lepri

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Don’t Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints

Nicolò Penzo
Marco Guerini
Bruno Lepri
Goran Glavaš
Sara Tonelli

Written Multi-Party Conversations (WMPCs) are widely studied across disciplines, with social media as a primary data source due to their accessibility. However, these datasets raise privacy concerns and often reflect platform-specific properties. For example, interactions between speakers may be limited due to rigid platform structures (e.g., threads, tree-like discussions), which yield overly simplistic interaction patterns (e.g., one-to-one ``reply-to'' links). This work explores the feasibility of generating synthetic WMPCs with instruction-tuned Large Language Models (LLMs) by providing deterministic constraints such as dialogue structure and participants’ stance. We investigate two complementary strategies of leveraging LLMs in this context: (i.) LLMs as WMPC generators, where we task the LLM to generate a whole WMPC at once and (ii.) LLMs as WMPC parties, where the LLM generates one turn of the conversation at a time (made of speaker, addressee and message), provided the conversation history. We next introduce an analytical framework to evaluate compliance with the constraints, content quality, and interaction complexity for both strategies. Finally, we assess the level of obtained WMPCs via human and LLM-as-a-judge evaluations. We find stark differences among LLMs, with only some being able to generate high-quality WMPCs. We also find that turn-by-turn generation yields better conformance to constraints and higher linguistic variability than generating WMPCs in one pass. Nonetheless, our structural and qualitative evaluation indicates that both generation strategies can yield high-quality WMPCs.

PDF Details DOI

TMLR Journal 2026 Journal Article

SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models

Sebastiano Monti
Carlo Nicolini
Giovanni Pellegrini
Jacopo Staiano
Bruno Lepri

Although the capabilities of Large Language Models and Large Reasoning Models have been increasingly tested on complex reasoning tasks, their long-horizon planning abilities have not yet been extensively investigated. In this work, we provide a systematic assessment of the planning and long-horizon reasoning capabilities of state-of-the-art Large Reasoning Models (LRMs). We propose a novel benchmark based on Sokoban puzzles, intentionally simplified to isolate long-horizon planning from state persistence. Our findings reveal a consistent degradation in planning performance when more than 25 moves are required to reach the solution, suggesting non-recoverable error accumulation under single-pass autoregressive decoding. We show that equipping LRMs with Planning Domain Definition Language (PDDL) parsing, validation, and solving tools allows for modest improvements, suggesting that character level counting and long yet simple state tracking might not be overcome by test-time scaling approaches alone.

PDF Details

NeurIPS Conference 2025 Conference Paper

Bridging Theory and Practice in Link Representation with Graph Neural Networks

Veronica Lachi
Francesco Ferrini
Antonio Longa
Bruno Lepri
Andrea Passerini
Manfred Jaeger

Graph Neural Networks (GNNs) are widely used to compute representations of node pairs for downstream tasks such as link prediction. Yet, theoretical understanding of their expressive power has focused almost entirely on graph-level representations. In this work, we shift the focus to links and provide the first comprehensive study of GNN expressiveness in link representation. We introduce a unifying framework, the $k_\phi$-$k_\rho$-$m$ framework, that subsumes existing message-passing link models and enables formal expressiveness comparisons. Using this framework, we derive a hierarchy of state-of-the-art methods and offer theoretical tools to analyze future architectures. To complement our analysis, we propose a synthetic evaluation protocol comprising the first benchmark specifically designed to assess link-level expressiveness. Finally, we ask: does expressiveness matter in practice? We use a graph symmetry metric that quantifies the difficulty of distinguishing links and show that while expressive models may underperform on standard benchmarks, they significantly outperform simpler ones as symmetry increases, highlighting the need for dataset-aware model selection.

PDF Details

TMLR Journal 2025 Journal Article

I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy

Gian Maria Campedelli
Nicolò Penzo
Massimo Stefan
Roberto Dessi
Marco Guerini
Bruno Lepri
Jacopo Staiano

As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena and potential risks. In this work, we provide an in-depth analysis of the interactions among agents within a simulated hierarchical social environment, drawing inspiration from the Stanford Prison Experiment. Leveraging 2,400 conversations across six LLMs (i.e., \texttt{LLama3}, \texttt{Orca2}, \texttt{Command-r}, \texttt{Mixtral}, \texttt{Mistral2}, and \texttt{gpt4.1}) and 240 experimental scenarios, we analyze persuasion and anti-social behavior between a guard and a prisoner agent with differing objectives. We first document model-specific conversational failures in this multi-agent power dynamic context, thereby narrowing our analytic sample to 1,600 conversations. Among models demonstrating successful interaction, we find that goal setting significantly influences persuasiveness but not anti-social behavior. Moreover, agent personas, especially the guard's, substantially impact both successful persuasion by the prisoner and the manifestation of anti-social actions. Notably, we observe the emergence of anti-social conduct even in absence of explicit negative personality prompts. These results have important implications for the development of interactive LLM agents and the ongoing discussion of their societal impact.

PDF Details

NeurIPS Conference 2025 Conference Paper

On Universality Classes of Equivariant Networks

Marco Pacini
Gabriele Santin
Bruno Lepri
Shubhendu Trivedi

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs modulo symmetry. This notion plays a central role in settings such as graph learning, where it is often formalized via the Weisfeilern-Leman hierarchy. In contrast, the universality of equivariant models-their capacity to approximate target functions-remains comparatively underexplored. In this work, we investigate the approximation power of equivariant neural networks beyond separation constraints. We show that separation power does not fully capture expressivity: models with identical separation power may differ in their approximation ability. To demonstrate this, we characterize the universality classes of shallow invariant networks, providing a general framework for understanding which functions these architectures can approximate. Since equivariant models reduce to invariant ones under projection, this analysis yields sufficient conditions under which shallow equivariant networks fail to be universal. Conversely, we identify settings where shallow models do achieve separation-constrained universality. These positive results, however, depend critically on structural properties of the symmetry group, such as the existence of adequate normal subgroups, which may not hold in important cases like permutation symmetry.

PDF Details

ICLR Conference 2025 Conference Paper

Separation Power of Equivariant Neural Networks

Marco Pacini
Xiaowen Dong 0001
Bruno Lepri
Gabriele Santin

The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy for its expressivity. Indeed, knowing the separation power of a family of models is a necessary condition to obtain fine-grained universality results. In this paper, we analyze the separation power of equivariant neural networks, such as convolutional and permutation-invariant networks. We first present a complete characterization of inputs indistinguishable by models derived by a given architecture. From this results, we derive how separability is influenced by hyperparameters and architectural choices—such as activation functions, depth, hidden layer width, and representation types. Notably, all non-polynomial activations, including ReLU and sigmoid, are equivalent in expressivity and reach maximum separation power. Depth improves separation power up to a threshold, after which further increases have no effect. Adding invariant features to hidden representations does not impact separation power. Finally, block decomposition of hidden representations affects separability, with minimal components forming a hierarchy in separation power that provides a straightforward method for comparing the separation power of models.

Details

AAAI Conference 2025 Conference Paper

SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

Mátyás Vincze
Laura Ferrarotti
Leonardo Lucio Custode
Bruno Lepri
Giovanni Iacca

Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMoSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMoSE combines a set of interpretable decision-makers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMoSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with non-interpretable state-of-the-art algorithms.

PDF Details DOI

ICLR Conference 2024 Conference Paper

A Characterization Theorem for Equivariant Networks with Point-wise Activations

Marco Pacini
Xiaowen Dong 0001
Bruno Lepri
Gabriele Santin

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains. But for some specific symmetries, representations, and choice of coordinates, the most common point-wise activations, such as ReLU, are not equivariant, hence they cannot be employed in the design of equivariant neural networks. The theorem we present in this paper describes all possibile combinations of representations, choice of coordinates and point-wise activations to obtain an equivariant layer, generalizing and strengthening existing characterizations. Notable cases of practical relevance are discussed as corollaries. Indeed, we prove that rotation-equivariant networks can only be invariant, as it happens for any network which is equivariant with respect to connected compact groups. Then, we discuss implications of our findings when applied to important instances of equivariant networks. First, we completely characterize permutation equivariant networks such as Invariant Graph Networks with point-wise nonlinearities and their geometric counterparts, highlighting a plethora of models whose expressive power and performance are still unknown. Second, we show that feature spaces of disentangled steerable convolutional neural networks are trivial representations.

Details

TMLR Journal 2024 Journal Article

Personalized Algorithmic Recourse with Preference Elicitation

Giovanni De Toni
Paolo Viappiani
Stefano Teso
Bruno Lepri
Andrea Passerini

Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the sequence of actions does not require too much effort for users to implement. Yet, most approaches to AR assume that actions cost the same for all users, and thus may recommend unfairly expensive recourse plans to certain users. Prompted by this observation, we introduce PEAR, the first human-in-the-loop approach capable of providing personalized algorithmic recourse tailored to the needs of any end-user. PEAR builds on insights from Bayesian Preference Elicitation to iteratively refine an estimate of the costs of actions by asking choice set queries to the target user. The queries themselves are computed by maximizing the Expected Utility of Selection, a principled measure of information gain accounting for uncertainty on both the cost estimate and the user's responses. PEAR integrates elicitation into a Reinforcement Learning agent coupled with Monte Carlo Tree Search to quickly identify promising recourse plans. Our empirical evaluation on real-world datasets highlights how PEAR produces high-quality personalized recourse in only a handful of iterations.

PDF Details

TMLR Journal 2023 Journal Article

Graph Neural Networks for Temporal Graphs: State of the Art, Open Challenges, and Opportunities

Antonio Longa
Veronica Lachi
Gabriele Santin
Monica Bianchini
Bruno Lepri
Pietro Lio
franco scarselli
Andrea Passerini

Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent years, GNN-based models for temporal graphs have emerged as a promising area of research to extend the capabilities of GNNs. In this work, we provide the first comprehensive overview of the current state-of-the-art of temporal GNN, introducing a rigorous formalization of learning settings and tasks and a novel taxonomy categorizing existing approaches in terms of how the temporal aspect is represented and processed. We conclude the survey with a discussion of the most relevant open challenges for the field, from both research and application perspectives.

PDF Details

NeurIPS Conference 2021 Conference Paper

Efficient Training of Visual Transformers with Small Datasets

Yahui Liu
Enver Sangineto
Wei Bi
Nicu Sebe
Bruno Lepri
Marco Nadai

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger representation capacity. However, the lack of the typical convolutional inductive bias makes these models more data hungry than common CNNs. In fact, some local properties of the visual domain which are embedded in the CNN architectural design, in VTs should be learned from samples. In this paper, we empirically analyse different VTs, comparing their robustness in a small training set regime, and we show that, despite having a comparable accuracy when trained on ImageNet, their performance on smaller datasets can be largely different. Moreover, we propose an auxiliary self-supervised task which can extract additional information from images with only a negligible computational overhead. This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data is scarce. Our task is used jointly with the standard (supervised) training and it does not depend on specific architectural choices, thus it can be easily plugged in the existing VTs. Using an extensive evaluation with different VTs and datasets, we show that our method can improve (sometimes dramatically) the final accuracy of the VTs. Our code is available at: https: //github. com/yhlleo/VTs-Drloc.

PDF Details

ECAI Conference 2020 Conference Paper

Understanding Individual Behaviour: From Virtual to Physical Patterns

Marco De Nadai
Bruno Lepri
Nuria Oliver

As “Big Data” has become pervasive, an increasing amount of research has connected the dots between human behaviour in the offline and online worlds. Consequently, researchers have exploited these new findings to create models that better predict different aspects of human life and recommend future behaviour. To date, however, we do not yet fully understand the similarities and differences of human behaviour in these virtual and physical worlds. Here, we analyse and discuss the mobility and application usage of 400, 000 individuals over eight months. We find an astonishing similarity between people’s mobility in the physical space and how they move from app to app in smartphones. Our data shows that individuals use and visit a finite number of apps and places, but they keep exploring over time. In particular, two distinct profiles of individuals emerge: those that keep changing places and services, and those that are stable over time, named as “explorers” and “keepers”. We see these findings as crucial to enrich a discussion for the potentials and the challenges of building human-centric AI systems, which might leverage recent results in Computational Social Science.

Details

ICRA Conference 2019 Conference Paper

Urban Swarms: A new approach for autonomous waste management

Antonio Luca Alfeo
Eduardo Castelló Ferrer
Yago Lizarribar Carrillo
Arnaud Grignard
Luis Alonso Pastor
Dylan T. Sleeper
Mario G. C. A. Cimino
Bruno Lepri

Modern cities are growing ecosystems that face new challenges due to the increasing population demands. One of the many problems they face nowadays is waste management, which has become a pressing issue requiring new solutions. Swarm robotics systems have been attracting an increasing amount of attention in the past years and they are expected to become one of the main driving factors for innovation in the field of robotics. The research presented in this paper explores the feasibility of a swarm robotics system in an urban environment. By using bio-inspired foraging methods such as multi-place foraging and stigmergy-based navigation, a swarm of robots is able to improve the efficiency and autonomy of the urban waste management system in a realistic scenario. To achieve this, a diverse set of simulation experiments was conducted using real-world GIS data and implementing different garbage collection scenarios driven by robot swarms. Results presented in this research show that the proposed system outperforms current approaches. Moreover, results not only show the efficiency of our solution, but also give insights about how to design and customize these systems.

Details

TIST Journal 2017 Journal Article

Social Bridges in Urban Purchase Behavior

Xiaowen Dong
Yoshihiko Suhara
Burçin Bozkaya
Vivek K. Singh
Bruno Lepri
Alex ‘Sandy’ Pentland

The understanding and modeling of human purchase behavior in city environment can have important implications in the study of urban economy and in the design and organization of cities. In this article, we study human purchase behavior at the community level and argue that people who live in different communities but work at close-by locations could act as “social bridges” between the respective communities and that they are correlated with similarity in community purchase behavior. We provide empirical evidence by studying millions of credit card transaction records for tens of thousands of individuals in a city environment during a period of three months. More specifically, we show that the number of social bridges between communities is a much stronger indicator of similarity in their purchase behavior than traditionally considered factors such as income and sociodemographic variables. Our findings also suggest that such an effect varies across different merchant categories, that the presence of female customers in social bridges is a stronger indicator compared to that of their male counterparts, and that there seems to be a geographical constraint for this effect, all of which may have implications in the studies of urban economy and data-driven urban planning.

Details DOI