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 this literature appropriates the terminology of MAS without engaging with its foundational principles. In this position paper, we highlight critical discrepancies between MAS theory and current MAS LLMs implementations, focusing on four key areas: the social aspect of agency, environment design, coordination and communication protocols, and measuring emergent behaviours. Our position is that many MAS LLMs lack multi-agent characteristics such as autonomy, social interaction, and structured environments, and often rely on oversimplified, LLM-centric architectures. The field may slow down and lose traction by revisiting problems the MAS literature has already addressed. Therefore, we systematically analyse this issue and outline associated research opportunities; we advocate for better integrating established MAS concepts and more precise terminology to avoid mischaracterisation and missed opportunities.

Cognitive Architectures are the forefront of the research into developing an artificial cognition. However, they approach the problem from a separated memory and program model of computation. This model of computation poses a fundamental problem: the knowledge retrieval heuristic. In this paper we propose to solve this problem by using a novel model of computation, one where memory and program are merged: the Function-Representation. This model of computation involves defining a generic Function-Representation and instantiating multiple instances of it. In this paper we explore the potential of this novel model of computation through mathematical definitions and proofs. We also explore the kind of functions a Function-Representation can implement, and present different ways to organise multiple instances of a Function-Representation.

Modelling and characterizing emergent behaviour within a swarm can pose significant challenges in terms of assurance. Assurance tasks encompass adherence to standards, certification processes, and the execution of verification and validation (V&V) methods, such as model checking. In this study, we propose a holistic, multi-level modelling approach for formally verifying and validating autonomous robotic swarms, which are defined at the macroscopic formal modelling, low-fidelity simulation, high-fidelity simulation, and real-robot levels. Our formal macroscopic models, used for verification, are characterized by data derived from actual simulations, ensuring both accuracy and traceability across different system models. Furthermore, our work combines formal verification with experimental validation involving real robots. In this way, our corroborative approach for V&V seeks to enhance confidence in the evidence, in contrast to employing these methods separately. We explore our approach through a case study focused on a swarm of robots operating within a public cloakroom. Swarm robotics offers a method for coordinating a large number of robots, inspired by swarm behaviours in nature [1]. The collective behaviours of a swarm are not directly engineered into the system. Rather, they arise due to interactions among individual robots and their environment, called emergent behaviour [2].

Interacting individuals in complex systems often give rise to coherent motion exhibiting coordinated global structures. Such phenomena are ubiquitously observed in nature, from cell migration, bacterial swarms, animal and insect groups, and even human societies. Primary mechanisms responsible for the emergence of collective behavior have been extensively identified, including local alignments based on average or relative velocity, non-local pairwise repulsive-attractive interactions such as distance-based potentials, interplay between local and non-local interactions, and cognitive-based inhomogeneous interactions. However, discovering how to adapt these mechanisms to modulate emergent behaviours remains elusive. Here, we demonstrate that it is possible to generate coordinated structures in collective behavior at desired moments with intended global patterns by fine-tuning an inter-agent interaction rule. Our strategy employs deep neural networks, obeying the laws of dynamics, to find interaction rules that command desired collective structures. The decomposition of interaction rules into distancing and aligning forces, expressed by polynomial series, facilitates the training of neural networks to propose desired interaction models. Presented examples include altering the mean radius and size of clusters in vortical swarms, timing of transitions from random to ordered states, and continuously shifting between typical modes of collective motions. This strategy can even be leveraged to superimpose collective modes, resulting in hitherto unexplored but highly practical hybrid collective patterns, such as protective security formations. Our findings reveal innovative strategies for creating and controlling collective motion, paving the way for new applications in robotic swarm operations, active matter organisation, and for the uncovering of obscure interaction rules in biological systems.

Many complex natural phenomena--such as organ growth, the structure of materials or the patterns of neural activity in our brains--are emergent [1]. These are typically characterised by many simple interacting components that collectively exhibit behaviour that is far richer than that of the individual parts, and cannot easily be predicted from them. Emergence is especially prevalent in complex systems of biological nature across a wide range of scales - from gene expression dictating cell fates, interacting cells forming structures during morphogenesis, synaptic connections in the brain, or the interactions of organisms in ecology. Cellular Automata (CA) provide simple models of spatio-temporal emergent behaviour, where a discrete lattice of'cells' are equipped with an internal state and a rule that updates each cell state depending on itself and its local neighbours. The classic Game of Life [2] is a famous example, where cell states and the update rule utilise simple Boolean logic, but the emergent complexity has fascinated and inspired much research [3, 4]. CA are a natural modelling framework of a wide range of biological processes such as: skin patterning [5, 6], limb polydactyly [7], chimerism [8], cancer [9] and landscape ecology [10]. In these cases the CA rules are constructed with expert knowledge of likely mechanisms, however in general the space of possible CA rules is vast, and there is a non-uniqueness by which several rules can result in qualitatively similar emergent behaviours. As such the inverse problem of inferring mechanistic interactions (CA rules) that might generate a given observed emergent behaviour is much more challenging than the forward problem.

Tracking an odour plume to locate its source under variable wind and plume statistics is a complex task. Flying insects routinely accomplish such tracking, often over long distances, in pursuit of food or mates. Several aspects of this remarkable behaviour and its underlying neural circuitry have been studied experimentally. Here we take a complementary in silico approach to develop an integrated understanding of their behaviour and neural computations. Specifically, we train artificial recurrent neural network agents using deep reinforcement learning to locate the source of simulated odour plumes that mimic features of plumes in a turbulent flow. Interestingly, the agents’ emergent behaviours resemble those of flying insects, and the recurrent neural networks learn to compute task-relevant variables with distinct dynamic structures in population activity. Our analyses put forward a testable behavioural hypothesis for tracking plumes in changing wind direction, and we provide key intuitions for memory requirements and neural dynamics in odour plume tracking. Olfactory navigation is a well-studied topic in insect behaviour, but many aspects of the challenging task of odour plume tracking are unknown. In a deep reinforcement learning approach, artificial agents are trained to produce (in silico) trajectories to localize the source of an odour plume, showing dynamics that mimic real insect behaviours.

In this paper, we present a geometric framework for the passive localisation of static emitters. The objective is to localise the position of the emitters in a given area by centralised coordination of mobile passive sensors. This framework uses only the geometry of the problem to minimise the maximal bounds of the emitters' locations without using a belief or probability distribution. This geometric approach provides effective boundaries on the emitters' position. It can also be useful in evaluating different decision-making strategies for coordinating mobile passive sensors and complementing statistical methods during the initialisation process. The effectiveness of the geometric approach is shown by designing and evaluating a greedy decision-making strategy, where a sensor selects its future position by minimising the maximum uncertainty on its next measurement using one of the global objective functions. Finally, we analyse and discuss the emergent behaviour and robustness of the proposed algorithms.

At Collison 2022 in Toronto last week, former Google chief executive officer Eric Schmidt shared his thoughts on where artificial intelligence (AI) is headed, and what dangers it's facing in the path of its rapid development. He opened the discussion by highlighting the evolving focus of the AI landscape. "If you look at the biggest thing 10 years ago… [it] was imaging, and in particular the fact that vision through things like image net and others would become better on computers than for humans." Schmidt said there are now two major pursuits in the current AI cycle. One is to understand the underlying principles of multi-dimensional input and output mapping.

We investigate the general problem of establishing whether a swarm satisfies an emergent property. We put forward a formal model for swarms that accounts for their nature of unbounded collections of agents following simple local protocols. We formally define the decision problem of determining whether a swarm satisfies an emergent property. We introduce a sound and complete procedure for solving the problem. We illustrate the technique by applying it to the Beta aggregation algorithm.