Andrei Ciortea

AAMAS Conference 2026 Conference Paper

Discovery and Enactment of Declarative Interaction Protocols in Dynamically Open Settings

• Andrei Ciortea
• Kai Schultz
• Amit K. Chopra
• Ganesh Ramanathan

We address the problem of enabling agents to interact flexibly in settings where protocols, participants, and the deployment context must be discovered at run time. Our approach synthesizes two complementary ideas: First, we leverage information protocols for flexible multi-agent interaction. Second, we adopt hypermediadriven interaction to decouple agents from their deployment context. Agents use hypermedia to discover protocol specifications and participantsincontext. Onceasuitableprotocolisfound, agentsuse metaprotocols for dynamic role binding, and hypermedia controls then guide the protocol enactment. We demonstrate our approach in a scenario in which agents start from a single entry URI to join an open marketplace, discover available items, protocols, buyers, and sellers, and successfully enact a protocol for buying and selling items. This shows that integrating information protocols with hypermedia-driven interaction enables highly flexible multi-agent coordination in dynamically open settings, such as the Web.

EUMAS Conference 2025 Conference Paper

astra-langchain4j: Experiences Combining LLMs and Agent Programming

• Rem W. Collier
• Katharine Beaumont
• Andrei Ciortea

EUMAS Conference 2025 Conference Paper

Extending CArtAgO to support the engineering of complex distributed environments at the Knowledge Level

• Alessandro Ricci
• Andrei Ciortea
• Samuele Burattini

EUMAS Conference 2025 Conference Paper

Towards a Distinct Programming Style for AgentSpeak(L)

• Rem W. Collier
• Katharine Beaumont
• Andrei Ciortea

AAMAS Conference 2024 Conference Paper

Enabling BDI Agents to Reason on a Dynamic Action Repertoire in Hypermedia Environments

• Danai Vachtsevanou
• Bruno de Lima
• Andrei Ciortea
• Jomi Fred Hübner
• Simon Mayer
• Jérémy Lemée

Autonomy requires adaptability and persistence in pursuing longterm objectives within evolving contexts. While BDI agents can cope with dynamic and uncertain environments, their adaptability is typically constrained by static action repertoires, known a priori by designers. Through Semantic Web and Web of Things technologies, machine-readable action descriptions can be discovered in hypermedia environments, and updated dynamically to mirror the evolving landscape of actions offered by real-world environments. This paper proposes the integration of action-oriented BDI reasoning with signifiers that reveal information about action possibilities that may appear, disappear, or be modified in a hypermedia environment at any time. We extend the means-end reasoning of BDI agents with a mechanism for resolving signifiers discovered at run time into actions, which enables agents to adjust their decisionmaking based on action possibilities advertised in the environment. We evaluate our approach through experiments, where Jason agents discover signifiers expressed with available Web ontologies. The results demonstrate that our signifier resolution mechanism enhances action reasoning at run time towards effective goal achievement in dynamic and unknown environments.

EUMAS Conference 2024 Conference Paper

Towards Agents' Embodiment in Hypermedia Multi-agent Systems

• Matteo Castellucci
• Samuele Burattini
• Andrei Ciortea
• Jérémy Lemée
• Danai Vachtsevanou
• Alessandro Ricci
• Simon Mayer

Abstract Situatedness and embodiment are central features of autonomous agents, initially inspired by agents operating in physical environments. In this paper, we discuss the benefits of situated and embodied agents in digital environments. More specifically, we study the embodiment of agents in Web-based Multi-Agent Systems (MAS). Such MAS are inherently open and distributed, as they inherit these properties from the Web, and increasingly dynamic, as they can easily extend to physical environments through the Web of Things. We propose a conceptualization of agent bodies in such Web environments and discuss their properties. We illustrate our approach through a demonstration scenario implemented using the Yggdrasil framework for Hypermedia MAS, a subset of Web-based MAS that follows a hypermedia-based design rationale.

AAMAS Conference 2023 Conference Paper

Domain-Expert Configuration of Hypermedia Multi-Agent Systems in Industrial Use Cases

• Jérémy Lemée
• Samuele Burattini
• Simon Mayer
• Andrei Ciortea

Based on the analysis of two real-world use cases for agriculture and manufacturing, we suggest that Hypermedia Multi-Agent Systems (MAS) are a viable option to interconnect and coordinate devices, services, machine-learning systems, and people in industrial scenarios. We propose and implement an architecture based on three components: an infrastructure that manages Web of Things environments and executes Hypermedia MAS, a visual development environment for programming agents, and a goal specification interface for end-users. While the infrastructure manages information flows between the system components and provides an environment for agents, the visual language enables domain experts to configure the behaviour of the system leveraging agent-oriented programming abstractions both at design time and run time, and the goal specification interface permits users to delegate goals to the running Hypermedia MAS while re-using domain vocabulary.

AAMAS Conference 2023 Conference Paper

Signifiers as a First-class Abstraction in Hypermedia Multi-Agent Systems

• Danai Vachtsevanou
• Andrei Ciortea
• Simon Mayer
• Jérémy Lemée

Hypermedia APIs enable the design of reusable hypermedia clients that discover and exploit affordances on the Web. However, the reusability of such clients remains limited since they cannot plan and reason about their interactions. This paper provides a conceptual bridge between hypermedia-driven affordance exploitation on the Web and methods for representing and reasoning about actions that have been extensively explored in Multi-Agent Systems (MAS) and, more broadly, Artificial Intelligence. We build on concepts and methods from Affordance Theory and Human-Computer Interaction to introduce signifiers as a first-class abstraction in Web-based MAS: Signifiers are designed with respect to the agent-environment context of their usage and enable agents with heterogeneous abilities to act and to reason about action. We define a formal model for the contextual exposure of signifiers in hypermedia environments that aims to drive affordance exploitation. We demonstrate our approach with a prototypical Web-based MAS where two agents with different reasoning abilities proactively discover how to interact with their environment by perceiving only the signifiers that fit their abilities. We show that signifier exposure based on the dynamic agent-environment context helps to facilitate effective and efficient interactions on the Web.

AAMAS Conference 2021 Conference Paper

Autonomous Agents on the Edge of Things

• Timotheus Kampik
• Andres Gomez
• Andrei Ciortea
• Simon Mayer

This paper describes a demonstration setup that integrates cognitive agents with the latest W3C standardization efforts for the Web of Things (WoT). The conceptual foundations of the implemented system are the integration of cognitive agent abstractions with W3C Web Things, which are generic abstractions of devices and virtual services that provide agents with various interaction affordances (e. g. , actions, events). Together with the W3C WoT Scripting API, which is an ECMAScript-compatible API for W3C WoT environments, these standards allow JavaScript-based agents to be deployed and to operate in heterogeneous WoT environments. The agents can then be effectively distributed across the physical-virtual space in a write once, run anywhere manner: we deploy agents across a heterogeneous information system landscape that includes Web servers, browser-based front-ends, and constrained devices (microcontrollers). The deployment only requires minor platform-specific adjustments to consider resource and performance limitations on constrained devices. As a running example, we demonstrate a semiautonomous assembly scenario with human-in-the-loop support.

AAMAS Conference 2019 Conference Paper

A Decade in Hindsight: The Missing Bridge Between Multi-Agent Systems and the World Wide Web

• Andrei Ciortea
• Simon Mayer
• Fabien Gandon
• Olivier Boissier
• Alessandro Ricci
• Antoine Zimmermann

The World Wide Web has evolved drastically over the past decade – and the proliferation of Web APIs has turned it into the middleware of choice for most distributed systems. The recent focus on hypermedia-driven APIs together with initiatives such as the Web of Things and Linked Data are now promoting and advancing the development of a new generation of dynamic, open, and long-lived systems on the Web. These systems require agent-based solutions to the point that Web researchers have started to build autonomous systems on their own. It is thus both timely and necessary to investigate and align the latest developments in Web research and multi-agent systems (MAS) research. In this paper, we analyze in hindsight the factors that hindered the widespread acceptance of early Web-based MAS. We argue that the answer lies equally in a lack of practical use cases as well as the premature development and alignment of Web and agent technologies. We then present our vision for a new generation of autonomous systems on the Web, which we call hypermedia MAS, together with the research opportunities and challenges they bring.

AAMAS Conference 2019 Conference Paper

Engineering Scalable Distributed Environments and Organizations for MAS

• Alessandro Ricci
• Andrei Ciortea
• Simon Mayer
• Olivier Boissier
• Rafael H. Bordini
• Jomi Fred Hubner

In MAS programming and engineering, the environment and the organisation can be exploited as first-class design and programming abstractions besides the agent one. A main example of a platform implementing this view is JaCaMo, which allows the programming of a MAS in terms of an organisation of cognitive agents sharing a common artifact-based environment. However, MAS models and platforms in general do not provide a satisfactory approach for MAS developers to uniformly deal with distribution at multiple dimensions — agent, environment, and organisation. Typically, environments are either centralised in a single node, or composed by parts that run on different nodes but with a poor support at the programming and execution levels to deal with that. In this paper, we tackle this problem by proposing a model for engineering world-wide distributed environments and organisations for MAS. The approach integrates the A&A (Agents and Artifacts) conceptual model with a web/resource-oriented view of distributed systems as proposed by the REST architectural style. To evaluate the approach, an extension of the JaCaMo open-source platform has been developed implementing the proposed model.

AAMAS Conference 2018 Conference Paper

Repurposing Manufacturing Lines on the Fly with Multi-agent Systems for the Web of Things

• Andrei Ciortea
• Simon Mayer
• Florian Michahelles

Multi-agent systems (MAS) have long been envisioned as a key enabling technology in manufacturing, but this promise is yet to be realized: the lack of proper models, architectures, tooling, and the high level of expertise required for designing and programming agent-based manufacturing systems have hindered their large-scale acceptance. The emerging Web of Things (WoT), now being standardized at the W3C and IETF, provides new research opportunities that could help MAS enter the mainstream. In this paper, we present an approach to design scalable and flexible agent-based manufacturing systems that integrates automated planning with multi-agent oriented programming for the WoT: autonomous agents synthesize production plans using semantic descriptions of Web-based artifacts and coordinate with one another via multi-agent organizations; engineers can program and repurpose the systems on the fly via an intuitive Web user interface. The systems use the Web as an application architecture (and not just as a transport layer), which facilitates the seamless integration of geographically distributed production cells. To demonstrate our approach, we implemented a prototypical production cell that uses industry-grade robots and an augmented reality interface for human workers. Together, these contributions demonstrate a means to achieve an intriguing vision for the forthcoming fourth industrial revolution: a global collective intelligence for manufacturing.

AAMAS Conference 2017 Conference Paper

Give Agents Some REST: A Resource-oriented Abstraction Layer for Internet-scale Agent Environments

• Andrei Ciortea
• Olivier Boissier
• Antoine Zimmermann
• Adina Magda Florea

In this paper, we claim that the World Wide Web provides a suitable middleware for Internet-scale, open, and humancentric multi-agent systems. The novelty of our approach is to design the agent environment as a hypermedia application. We apply REST, the architectural style of the Web, to introduce a resource-oriented abstraction layer that decouples the application environment from its deployment context. Higher-level environment abstractions can then be implemented on top of this lower-level abstraction layer. To demonstrate our approach, we implemented a multi-agent application for the Internet of Things in which software agents can seamlessly navigate, use, and cooperate in an environment deployed over multiple Web services (e. g. , Facebook, Twitter) and constrained devices.