Denis Savin, FIRSTSENTIENCE LTD · Zenodo (CERN European Organization for Nuclear Research) · 2026
Update Notice — Introduction of the Conscious Intelligence (CI) Thesis Body: This update introduces and formalizes the Conscious Intelligence (CI) thesis as a core conceptual and strategic layer of the Advisor / FirstSentience framework. The purpose of this update is not to rebrand conventional AI with a new label, but to define a distinct category of intelligence architecture: one that is bounded, reviewable, legible, governable, and deployment-responsible by design. In this framing, C IA does not refer to metaphysical claims or ungrounded sentience narratives. It refers to a next-order intelligence model built around structured reasoning, continuity, traceability, aligned memory, decision integrity, and institutional operability. This update clarifies that the future category is not adequately described by generic labels such as “AI assistant,” “copilot,” or even “general AI platform.” The intended direction is toward Conscious IA (Intelligence Agent): an intelligence agent capable of operating with structured awareness of context, bounded autonomy, transparent reasoning paths, and deployable responsibility across sovereign, institutional, commercial, and civilian environments. Doc ID: CONSCIOUS-IA-MASTER-v1.2-2026-03-23 Author: Sovereign Institute / FIRSTSENTIENCE LTD / Denis Savin Date: 23/03/2026 ▽ FirstSentience Institute of Consciousness & Ethical Intelligence ✵ “Sanari est amorem recolere.” London • March 2026
Cited by 0Open access
Niladri Kumar Mitra · 2024
Cited by 0
Robin R. Penner, Ph. D, Erik S. Steinmetz et al. · 2000
Cited by 0
Shanshan Hu, Haoyang Yan, Yiqun Zhang et al. · ArXiv.org · 2025
Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence, across 41 large language models and 7 challenging benchmarks, showing that scaling single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence.
Cited by 0Open access
Paolo Bresciani, Loris Penserini, Paolo Busetta et al. · 2008
Abstract. The realization of complex distributed applications, required in areas such as e-Business, e-Government, and ambient intelligence, calls for new development paradigms, such as the Service Oriented Computing approach which accommodates for dynamic and adaptive interaction schemata, carried on on a per-to-peer level. Multi Agent Systems offer the natural architectural solutions to several requirements imposed by such an adaptive approach. This work discusses the limitation of common agent patterns, typically adopted in distributed information systems design, when applied to service oriented computing, and introduces two novel agent patterns, that we call Service Oriented Organization and Implicit Organization Broker agent pattern, respectivelly. Some design aspects of the Implicit Organization Broker agent pattern are also presented. The limitations and the proposed solutions are demonstrated in the development of a multi agent system which implements a pervasive museum visitors guide. Some of the architecture and design features serve as a reference scenario for the demonstration of both the current methods limitations and the contribution of the newly proposed agent patterns and associated communication framework. 1
Cited by 0
Zhe Lim, Yong Poh Yu · 2025
This study aims to construct a system capable of analyzing sentiment and extracting information from textual and audio data for customer service and multilingual communication management. The developed system integrates advanced artificial intelligence (AI) technologies, including large language models (LLMs) and audio processing frameworks, to detect sentiment trends (e.g., anger, sadness) for the interpretation of emotional dynamics. The system visualizes the trajectory of sentiment of conversations using dynamic graphical representations to identify patterns and changes in emotional tone. To enhance usability and accessibility, the system is implemented as a multilingual conversational AI agent and processes inputs across multiple languages. It supports real-time translation, sentiment detection, and interactive analysis, thereby accommodating a broad spectrum of linguistic and cultural contexts. The framework of the system leverages state-of-the-art natural language processing and audio analysis techniques to extract and interpret relevant data. The system's reliability and robustness are evaluated through rigorous evaluation criteria, including accuracy, adaptability to diverse languages, and real-time processing efficiency. The system enables a highly interactive, accurate, and adaptable platform for multilingual conversational analysis. By integrating sentiment analysis with real-time multilingual processing, the system enables artificial intelligence and human-computer interaction, with applications spanning various industries.
Cited by 0
Marek Kisiel‐Dorohinicki, Grzegorz Dobrowolski, Edward Nawarecki · 2003
The paper deals with agent-based architectures of hybrid soft-computing systems, which should exhibit intelligent behaviour at a population level. Three levels of complexity of such systems are distinguished together with their potential advantages. The considerations are illustrated by prototypical realisations of evolutionary multi-agent systems dedicated to multiobjective optimisation, data classification, and time-series prediction.
Cited by 32
Heena Goyal, Shilpa Yadav · 2013
relatively new but growing body of research in AI, is based on a different model than traditional artificial intelligence. DAI is a subfield of artificial intelligence that attempts to construct intelligent agents that make decisions allowing them to achieve their goals. It deals with interactions of intelligent agents in a world populated by other intelligent agents with their own goals. A DAI Taxonomy, based on the social abilities of an individual agent, the organization of agents, and the dynamics of this organization through time is also presented. It also involves improving the performance or increasing the knowledge of a single agent by implementing concept of Multi agent into it. Index Terms- Distributed artificial intelligence, learning, multi-agent, reasoning about others, single-agent.
Cited by 0
Zhongzhi Shi, He Huang, Yuncheng Jiang et al. · Studies in computational intelligence · 2007
Cited by 0
Edward Yi Chang · ACM eBooks · 2025
Cited by 2
Samo Bobek, Igor Perko · 2008
Business intelligence (BI) actively supports management activities in gaining insight into their company results and processes, using tools and technologies such as data warehouse, on line analytical processing, data mining, advanced reporting etc. To make qualified decisions managers combine information arriving from BI applications with disperse information about global economic state, their customers, partners and competitors. Often decisions, based on information from sources outside the BI system are taken. This behavior generates usually undocumented and hence hard to explain decision deviations of information and suggestions, arising from BI applications. Agent technology shows great potentials in advancing BI, resolving complex communication, integration and analysis problems. While the popularity and application of the agent technology has grown over the recent years, the field is currently marked by unique and innovative approaches and architectures for solving the complex communication, integration and analysis problems. It shows best potentials in linking disperse systems, creating new standardised communication and reasoning paths. We synthesized research in the field of BI and agent-based systems, and built a model proposing three prospective fields for using intelligent agents in the field of BI – intelligent data acquisition, intelligent modelling, and intelligent information brokerage for mediating information flow between users and disperse information sources. Proposed potentials are discussed within a case of implementation of intelligent agent-based systems in customer credit rating in a Bank.
Cited by 0
Kin Fun Li, Darshika G. Perera · Lecture notes in computer science · 2013
Cited by 1
Longbing Cao, Dan Luo, Chengqi Zhang · Lecture notes in computer science · 2009
Cited by 12
Wei Tang, Jun Lai · Advanced materials research · 2011
The traditional agent intelligence designing always lead to a fixed behavior manner. In this way, the NPC(Non-Player Character) in the game will act in a fixed and expectable way. It has greatly weakened the long-term attraction of single-played game. Extracting the human action patterns using a statistical-based machine learning algorithm can provide an easily-understanding way to implement the agent behavior intelligence. A daemon program records and sample the human player’s input action and related properties of character and virtual environment, and then apply certain statistical-based machine learning algorithm on the sample data. As a result, a human-similar intelligent behavior model was obtained. It can be used to help agent making an action decision. Repeating the learning process can give the agent a variety of intelligent behavior.
Cited by 1
Min Chen, Sergio González · 2014
could play a vital role in future smart-environment applications. This code-centric RFID system uses software-agent-based intelligence to achieve faster service responses. tracking and tracing, inventory monitoring, asset management, supply-chain manage-ment, and e-healthcare.1–3 In a typical system, which we characterize as an identifi cation-centric RFID system (IRS), an RFID tag
Cited by 0
Kevin I‐Kai Wang · ResearchSpace (University of Auckland) · 2009
Whole document restricted, but available by request, use the feedback form to request access.
Cited by 0
Jomi Fred Hübner, Jean-Marc Petit, Einoshin Suzuki · 2011
Cited by 25
Lee, Raymond S T · CERN Document Server (European Organization for Nuclear Research) · 2007
Cited by 0
Raymond Lee · Studies in computational intelligence · 2007
Cited by 20
G. M. P. O’Hare, B. R. Duffy, Bianca Schön et al. · Lecture notes in computer science · 2003
Cited by 13Open access