Abstract--This paper introduces Agentic-AI Healthcare, a privacy-aware, multilingual, and explainable research prototype developed as a single-investigator project. The platform integrates a dedicated Privacy & Compliance Layer that applies role-based access control (RBAC), AES-GCM field-level encryption, and tamper-evident audit logging, aligning with major healthcare data protection standards such as HIPAA (US), PIPEDA (Canada), and PHIPA (Ontario). Example use cases demonstrate multilingual patient-doctor interaction (English, French, Arabic) and transparent diagnostic reasoning powered by large language models. As an applied AI contribution, this work highlights the feasibility of combining agentic orchestration, multilingual accessibility, and compliance-aware architecture in healthcare applications. This platform is presented as a research prototype and is not a certified medical device. This paper presents a working prototype that integrates agentic orchestration via the Model Context Protocol (MCP), field-level encryption, and multilingual LLM agents into a single compliance-aware stack for healthcare.

Although numerous strategies have recently been proposed to enhance the autonomous interaction capabilities of multimodal agents in graphical user interface (GUI), their reliability remains limited when faced with complex or out-of-domain tasks. This raises a fundamental question: Are existing multimodal agents reasoning spuriously? In this paper, we propose \textbf{Agent-ScanKit}, a systematic probing framework to unravel the memory and reasoning capabilities of multimodal agents under controlled perturbations. Specifically, we introduce three orthogonal probing paradigms: visual-guided, text-guided, and structure-guided, each designed to quantify the contributions of memorization and reasoning without requiring access to model internals. In five publicly available GUI benchmarks involving 18 multimodal agents, the results demonstrate that mechanical memorization often outweighs systematic reasoning. Most of the models function predominantly as retrievers of training-aligned knowledge, exhibiting limited generalization. Our findings underscore the necessity of robust reasoning modeling for multimodal agents in real-world scenarios, offering valuable insights toward the development of reliable multimodal agents.

This work presents a novel representation learning framework, interactive world latent (IWoL), to facilitate team coordination in multi-agent reinforcement learning (MARL). Building effective representation for team coordination is a challenging problem, due to the intricate dynamics emerging from multi-agent interaction and incomplete information induced by local observations. Our key insight is to construct a learnable representation space that jointly captures inter-agent relations and task-specific world information by directly modeling communication protocols. This representation, we maintain fully decentralized execution with implicit coordination, all while avoiding the inherent drawbacks of explicit message passing, e.g., slower decision-making, vulnerability to malicious attackers, and sensitivity to bandwidth constraints. In practice, our representation can be used not only as an implicit latent for each agent, but also as an explicit message for communication. Across four challenging MARL benchmarks, we evaluate both variants and show that IWoL provides a simple yet powerful key for team coordination. Moreover, we demonstrate that our representation can be combined with existing MARL algorithms to further enhance their performance.

GUI grounding is the task of mapping natural language instructions to precise pixel coordinates in graphical user interfaces, enabling autonomous agents to interact with software as humans do (Zhang et al., 2025a; Wang et al., 2024a; Zheng et al., 2024). This capability is fundamental for computer automation: without accurate grounding, agents cannot click buttons, fill forms, or navigate interfaces reliably. Although early approaches relied on structured metadata from HTML/DOM trees or accessibility APIs (Li et al., 2020; Deng et al., 2023), these methods face significant limitations: they require access to the underlying UI structure, which is often unavailable in desktop applications, inconsistent across platforms, or completely absent in legacy systems. Pure vision-based grounding, which operates directly on screenshots, offers universal applicability across any visual interface without requiring special access or instrumentation (Qin et al., 2025; Wang et al., 2025b; Guo et al., 2025). This approach mirrors human interaction with GUIs and enables automation of any software visible on screen, from modern web applications to legacy desktop tools. Current vision-based approaches typically formulate GUI grounding as a coordinate generation task, where models output pixel positions as text tokens (e.g., "x=523, y=217").

Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems struggle with complex datasets containing multiple files and iterative refinement. Existing approaches, including simple single- or multi-agent systems, often oversimplify the task, focusing on initial query parsing while failing to robustly manage data complexity, code errors, or final visualization quality. In this paper, we reframe this challenge as a collaborative multi-agent problem. We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection. We formalize this pipeline, demonstrating how metadata-focused analysis bypasses token limits and quality-driven refinement ensures robustness. Extensive evaluations show CoDA achieves substantial gains in the overall score, outperforming competitive baselines by up to 41.5%. This work demonstrates that the future of visualization automation lies not in isolated code generation but in integrated, collaborative agentic workflows.

The integration of Large Language Models (LLMs) into multiagent systems has opened new possibilities for collaborative reasoning and cooperation with AI agents. This paper explores different prompting methods and evaluates their effectiveness in enhancing agent collaborative behaviour and decision-making. We enhance CoELA, a framework designed for building Collaborative Embodied Agents that leverage LLMs for multi-agent communication, reasoning, and task coordination in shared virtual spaces. Through systematic experimentation, we examine different LLMs and prompt engineering strategies to identify optimised combinations that maximise collaboration performance. Furthermore, we extend our research by integrating speech capabilities, enabling seamless collaborative voice-based interactions. Our findings highlight the effectiveness of prompt optimisation in enhancing collaborative agent performance; for example, our best combination improved the efficiency of the system running with Gemma3 by 22% compared to the original CoELA system. In addition, the speech integration provides a more engaging user interface for iterative system development and demonstrations.

Abstract-- This paper presents a novel framework for estimating the position and orientation of flexible manipulators undergoing vertical motion using multiple inertial measurement units (IMUs), optimized and calibrated with ground truth data. The flexible links are modeled as a series of rigid segments, with joint angles estimated from accelerometer and gyroscope measurements acquired by cost-effective IMUs. A complementary filter is employed to fuse the measurements, with its parameters optimized through particle swarm optimization (PSO) to mitigate noise and delay. T o further improve estimation accuracy, residual errors in position and orientation are compensated using radial basis function neural networks (RBFNN). Experimental results validate the effectiveness of the proposed intelligent multi-IMU kinematic estimation method, achieving root mean square errors (RMSE) of 0.00021 m, 0.00041 m, and 0.00024 rad for y, z, and θ, respectively.

We investigate a public announcement logic for asynchronous public announcements wherein the sending of the announcements by the environment is separated from the reception of the announcements by the individual agents. Both come with different modalities. In the logical semantics, formulas are interpreted in a world of a Kripke model but given a history of prior announcements and receptions of announcements that already happened. An axiomatisation AA for such a logic has been given in prior work, for the formulas that are valid when interpreted in the Kripke model before any such announcements have taken place. This axiomatisation is a reduction system wherein one can show that every formula is equivalent to a purely epistemic formula without dynamic modalities for announcements and receptions. We propose a generalisation AA* of this axiomatisation, for the formulas that are valid when interpreted in the Kripke model given any history of prior announcements and receptions of announcements. It does not extend the axiomatisation AA, for example it is no longer valid that nobody has received any announcement. Unlike AA, this axiomatisation AA* is infinitary and it is not a reduction system.

Distributed optimization finds applications in large-scale machine learning, data processing and classification over multi-agent networks. In real-world scenarios, the communication network of agents may encounter latency that may affect the convergence of the optimization protocol. This paper addresses the case where the information exchange among the agents (computing nodes) over data-transmission channels (links) might be subject to communication time-delays, which is not well addressed in the existing literature. Our proposed algorithm improves the state-of-the-art by handling heterogeneous and arbitrary but bounded and fixed (time-invariant) delays over general strongly-connected directed networks. Arguments from matrix theory, algebraic graph theory, and augmented consensus formulation are applied to prove the convergence to the optimal value. Simulations are provided to verify the results and compare the performance with some existing delay-free algorithms.

Social media platforms are central to communication, yet their designs remain narrowly focused on engagement and scale. While researchers have proposed alternative visions for online spaces, these ideas are difficult to prototype within platform constraints. In this paper, we introduce a metaphor-driven system to help users imagine and explore new social media environments. The system translates users' metaphors into structured sets of platform features and generates interactive simulations populated with LLM-driven agents. To evaluate this approach, we conducted a study where participants created and interacted with simulated social media spaces. Our findings show that metaphors allow users to express distinct social expectations, and that perceived authenticity of the simulation depended on how well it captured dynamics like intimacy, participation, and temporal engagement. We conclude by discussing how metaphor-driven simulation can be a powerful design tool for prototyping alternative social architectures and expanding the design space for future social platforms.