Vito Trianni

Fabio Oddi, Andreagiovanni Reina, Vito Trianni

Quorum Sensing (QS) is a key capability for robot swarms, useful for coordination of activities at the group level. Effective communication is instrumental for individuals to estimate the quorum level of the entire swarm. Anonymous communication protocols where individuals exchange local information without revealing unique identities are helpful to support quorum estimates by sampling information from neighbours and maintain scalability of the QS process. However, because anonymous protocols cannot distinguish message sources, repeated messages from the same sender may be double-counted, thereby biasing collective quorum estimates. In this study, we introduce a stochastic filtering protocol inspired by $k$-priority sampling to improve estimate stability (\ANTk), and we compare it with a baseline anonymous protocols (\AN) and a randomised variant designed to improve accuracy (\ANT). We find that the baseline protocol \AN provides a parsimonious and fast solution, but remains highly inaccurate due to double-counting bias. The \ANT variant improves accuracy but suffers from information inertia, resulting in slower convergence. Finally, actively filtering the message buffer via the \ANTk protocol successfully decreases temporary errors and stabilises the estimate, at the cost of an increased time of recovery from errors.

Emanuele Masiero, Vito Trianni, Giuseppe Vizzari et al.

Precision agriculture requires efficient autonomous systems for crop monitoring, where agents must explore large-scale environments while minimizing resource consumption. This work addresses the problem as an active exploration task in a grid environment representing an agricultural field. Each cell may contain targets (e.g., damaged crops) observable from nine predefined points of view (POVs). Agents must infer the number of targets per cell using partial, sequential observations. We propose a two-stage deep learning framework. A pre-trained LSTM serves as a belief model, updating a probabilistic map of the environment and its associated entropy, which defines the expected information gain (IG). This allows agents to prioritize informative regions. A key contribution is the inclusion of a POV visibility mask in the input, preserving the Markov property under partial observability and avoiding revisits to already explored views. Three agent architectures were compared: an untrained IG-based agent selecting actions to maximize entropy reduction; a DQN agent using CNNs over local 3x3 inputs with belief, entropy, and POV mask; and a Double-CNN DQN agent with wider spatial context. Simulations on 20x20 maps showed that the untrained agent performs well despite its simplicity. The DQN agent matches this performance when the POV mask is included, while the Double-CNN agent consistently achieves superior exploration efficiency, especially in larger environments. Results show that uncertainty-aware policies leveraging entropy, belief states, and visibility tracking lead to robust and scalable exploration. Future work includes curriculum learning, multi-agent cooperation with shared rewards, transformer-based models, and intrinsic motivation mechanisms to further enhance learning efficiency and policy generalization.

N. Zöller, J. Berger, I. Lin et al.

Artificial intelligence systems, particularly large language models (LLMs), are increasingly being employed in high-stakes decisions that impact both individuals and society at large, often without adequate safeguards to ensure safety, quality, and equity. Yet LLMs hallucinate, lack common sense, and are biased - shortcomings that may reflect LLMs' inherent limitations and thus may not be remedied by more sophisticated architectures, more data, or more human feedback. Relying solely on LLMs for complex, high-stakes decisions is therefore problematic. Here we present a hybrid collective intelligence system that mitigates these risks by leveraging the complementary strengths of human experience and the vast information processed by LLMs. We apply our method to open-ended medical diagnostics, combining 40,762 differential diagnoses made by physicians with the diagnoses of five state-of-the art LLMs across 2,133 medical cases. We show that hybrid collectives of physicians and LLMs outperform both single physicians and physician collectives, as well as single LLMs and LLM ensembles. This result holds across a range of medical specialties and professional experience, and can be attributed to humans' and LLMs' complementary contributions that lead to different kinds of errors. Our approach highlights the potential for collective human and machine intelligence to improve accuracy in complex, open-ended domains like medical diagnostics.

Axel Abels, Tom Lenaerts, Vito Trianni et al.

Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm - expertise trees - that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.

Axel Abels, Tom Lenaerts, Vito Trianni et al.

Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Multiple expert judgements, whether human or artificial, can help in taking correct decisions, especially when exploration of alternative solutions is costly. As expert opinions might deviate, the problem of finding the right alternative can be approached as a collective decision making problem (CDM) via aggregation of independent judgements. Current state-of-the-art approaches focus on efficiently finding the optimal expert, and thus perform poorly if all experts are not qualified or if they are overly biased, thereby potentially derailing the decision-making process. In this paper, we propose a new algorithmic approach based on contextual multi-armed bandit problems (CMAB) to identify and counteract such biased expertise. We explore homogeneous, heterogeneous and polarised expert groups and show that this approach is able to effectively exploit the collective expertise, outperforming state-of-the-art methods, especially when the quality of the provided expertise degrades. Our novel CMAB-inspired approach achieves a higher final performance and does so while converging more rapidly than previous adaptive algorithms.

Roman Miletitch, Andreagiovanni Reina, Marco Dorigo et al.

In this study, we investigate the emergence of naming conventions within a swarm of robots that collectively forage, that is, collect resources from multiple sources in the environment. While foraging, the swarm explores the environment and makes a collective decision on how to exploit the available resources, either by selecting a single source or concurrently exploiting more than one. At the same time, the robots locally exchange messages in order to agree on how to name each source. Here, we study the correlation between the task-induced interaction network and the emergent naming conventions. In particular, our goal is to determine whether the dynamics of the interaction network are sufficient to determine an emergent vocabulary that is potentially useful to the robot swarm. To be useful, linguistic conventions need to be compact and meaningful, that is, to be the minimal description of the relevant features of the environment and of the made collective decision. We show that, in order to obtain a useful vocabulary, the task-dependent interaction network alone is not sufficient but it must be combined with a correlation between language and foraging dynamics. On the basis of these results, we propose a decentralised algorithm for collective categorisation which enables the swarm to achieve a useful -- compact and meaningful -- naming of all the available sources. Understanding how useful linguistic conventions emerge contributes to the design of robot swarms with potentially improved autonomy, flexibility, and self-awareness.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization can be broadly defined as the ability of a system to display ordered spatio-temporal patterns solely as the result of the interactions among the system components. Processes of this kind characterize both living and artificial systems, making self-organization a concept that is at the basis of several disciplines, from physics to biology and engineering. Placed at the frontiers between disciplines, Artificial Life (ALife) has heavily borrowed concepts and tools from the study of self-organization, providing mechanistic interpretations of life-like phenomena as well as useful constructivist approaches to artificial system design. Despite its broad usage within ALife, the concept of self-organization has been often excessively stretched or misinterpreted, calling for a clarification that could help with tracing the borders between what can and cannot be considered self-organization. In this review, we discuss the fundamental aspects of self-organization and list the main usages within three primary ALife domains, namely "soft" (mathematical/computational modeling), "hard" (physical robots), and "wet" (chemical/biological systems) ALife. We also provide a classification to locate this research. Finally, we discuss the usefulness of self-organization and related concepts within ALife studies, point to perspectives and challenges for future research, and list open questions. We hope that this work will motivate discussions related to self-organization in ALife and related fields.

Carlos Gershenson, Vito Trianni, Justin Werfel et al.

Self-organization has been an important concept within a number of disciplines, which Artificial Life (ALife) also has heavily utilized since its inception. The term and its implications, however, are often confusing or misinterpreted. In this work, we provide a mini-review of self-organization and its relationship with ALife, aiming at initiating discussions on this important topic with the interested audience. We first articulate some fundamental aspects of self-organization, outline its usage, and review its applications to ALife within its soft, hard, and wet domains. We also provide perspectives for further research.

Vito Trianni, Daniele De Simone, Andreagiovanni Reina et al.

Consensus dynamics in decentralised multiagent systems are subject to intense studies, and several different models have been proposed and analysed. Among these, the naming game stands out for its simplicity and applicability to a wide range of phenomena and applications, from semiotics to engineering. Despite the wide range of studies available, the implementation of theoretical models in real distributed systems is not always straightforward, as the physical platform imposes several constraints that may have a bearing on the consensus dynamics. In this paper, we investigate the effects of an implementation of the naming game for the kilobot robotic platform, in which we consider concurrent execution of games and physical interferences. Consensus dynamics are analysed in the light of the continuously evolving communication network created by the robots, highlighting how the different regimes crucially depend on the robot density and on their ability to spread widely in the experimental arena. We find that physical interferences reduce the benefits resulting from robot mobility in terms of consensus time, but also result in lower cognitive load for individual agents.