Maritime traffic management in busy ports faces growing challenges due to increased vessel traffic and complex waterway interactions. Strategies such as e-navigation by the International Maritime Organization aim to enhance navigation safety through traffic digitization. Maritime traffic simulation is essential for these systems, offering a virtual environment to model, analyze, and optimize traffic flows. Unlike road traffic, there are few simulators for maritime traffic, and they often lack realism and multi-ship interactions. In this paper, we (a) present ShipNaviSim, a data-driven maritime traffic simulator that utilizes a large-scale dataset over 2 years and electronic navigation charts to model vessel movements in Singapore Strait, one of the busiest ports in the world; (b) implement and evaluate different imitation learning algorithms such as behavior cloning to learn a policy that can accurately simulate real world vessel movements and multi-ship interactions; (c) develop vessel-specific metrics such as trajectory curvature, near miss rate, to validate the learned policy's alignment with human expert data. Extensive testing shows that our learned agents can behave like human experts, and thus can be used with the simulator for recommending routes for vessels in a hotspot region or generating diverse traffic scenarios to benchmark navigation systems.
This paper examines the effects of an aging population on key macroeconomic factors, including unemployment, labor market tightness, firm revenue, and product prices. Using a combination of agent-based and statistical models, we find that a rising old-age dependency ratio is associated with higher unemployment rates and lower firm revenue.
This paper describes ChatBDI, a framework for extending Beliefs-Desires-Intentions (BDI) agents with the ability to communicate with humans exploiting Large Language Models (LLMs). The ChatBDI integration of BDI agents and LLMs relies on the Knowledge Query and Manipulation Language (KQML) as the intermediary language between humans and agents, and Jason - inside the JaCaMo framework - as the implementation language. The purpose of ChatBDI is not only to create brand new 'BDI speakers', but also to add communication capabilities to existing BDI agents without altering their source code. This 'chattification' serves a double purpose: by exploiting the BDI model, it provides an 'intentional brain' to LLMs, hence addressing one of their major limitations as speakers - the lack of intentionality; by exploiting the generative power of LLMs, it adds a creative and fluent 'language actuator' to BDI agents.
Effective communication is essential in multi-agent reinforcement learning (MARL) for coordinating actions and maximizing collective rewards. Two common approaches for establishing communication are Graph Neural Networks (GNNs) and Transformers. Both methods introduce communication redundancy in complex scenarios. GNN-based methods model agent relationships through entire graph structures, leading to increased computational time. Transformers also increase computations due to self-attention calculations at each node. In this study, the ACORN (Acyclic Coordination with Reachability Networks) framework was introduced, utilizing acyclic coordination combined with a reachability-based attention mechanism. The most relevant nodes and connections in the GNN graph are used for self-attention calculations. Time complexity is reduced to O(vertical bar V vertical bar x nk x d), which is significantly better than the.O(vertical bar V vertical bar(2)d) complexity of standard Transformers. Acyclicity is ensured through Auto-Regressive Policy Learning and Sequence-Based Critic Learning. Experiments demonstrate that ACORN outperforms state-of-the-art methods, achieving an average improvement of 11% over MAT in challenging SMACV2 tasks and a 17% improvement within the same training time and steps.
Recent advances in large language models (LLMs) have enabled the development of LLM agents-autonomous systems capable of perceiving their environment, reasoning about tasks, and taking actions using external tools. While existing LLM-based Multi-Agent Systems (LaMAS) have shown promising results, they are predominantly centralized, operating within specific tasks or scenarios. These centralized designs simplify coordination but are fundamentally constrained by the limited data and knowledge available within a single entity. As LLM agents see broader deployment, the complexity of tasks increasingly requires collaboration across multiple organizations and data domains. Since organizations cannot and will not fully share their proprietary data, the next frontier of artificial intelligence lies in collective intelligence through decentralized LLM-based Multi-Agent Systems (LaMAS), where LLM agents, each accessing proprietary knowledge and tools, collaborate to solve complex tasks. This paradigm is becoming not just possible but necessary with the growing adoption of LLM agents across diverse organizations. This paper explores the transformative potential of decentralized LaMAS. In decentralized settings, two key issues arise: (1) privacy-preserving mechanisms that enable meaningful collaboration while safeguarding proprietary data and knowledge, and (2) monetization and credit attribution mechanisms that incentivize continuous improvement of agent capabilities and ensure fair value distribution among participants. Our analysis reveals that addressing these challenges can unlock a new paradigm of artificial collective intelligence that overcomes the limitations. This work contributes to decentralized AI by proposing a practical framework for mechanism design that advances both technological innovation and economic sustainability in decentralized LLM Agent networks.
