As the global population ages, artificial intelligence (AI)-powered agents have emerged as potential tools to support older adults' caregiving. Prior research has explored agent autonomy by identifying key interaction stages in task processes and defining the agent's role at each stage. However, ensuring that agents align with older adults' autonomy preferences remains a critical challenge. Drawing on interdisciplinary conceptualizations of autonomy, this paper examines four key dimensions of autonomy for older adults: decision-making autonomy, goal-oriented autonomy, control autonomy, and social responsibility autonomy. This paper then proposes the following research directions: (1) Addressing social responsibility autonomy, which concerns the ethical and social implications of agent use in communal settings; (2) Operationalizing agent autonomy from the task perspective; and (3) Developing autonomy measures.

The growing ubiquity of artificial intelligence (AI), in particular large language models (LLMs), has profoundly altered the way in which learners gain knowledge and interact with learning material, with many claiming that AI positively influences their learning achievements. Despite this advancement, current AI tutoring systems face limitations associated with their reactive nature, often providing direct answers without encouraging deep reflection or incorporating structured pedagogical tools and strategies. This limitation is most apparent in the field of mathematics, in which AI tutoring systems remain underdeveloped. This research addresses the question: How can AI tutoring systems move beyond providing reactive assistance to enable structured, individualized, and tool-assisted learning experiences? We introduce a novel multi-agent AI tutoring platform that combines adaptive and personalized feedback, structured course generation, and textbook knowledge retrieval to enable modular, tool-assisted learning processes. This system allows students to learn new topics while identifying and targeting their weaknesses, revise for exams effectively, and practice on an unlimited number of personalized exercises. This article contributes to the field of artificial intelligence in education by introducing a novel platform that brings together pedagogical agents and AI-driven components, augmenting the field with modular and effective systems for teaching mathematics.

While modern AI continues to advance, the biological brain remains the pinnacle of neural networks in its robustness, adaptability, and efficiency. This review explores an AI architectural path inspired by the brain's structure, particularly the minicolumn hypothesis, which views the neocortex as a distributed system of repeated modules - a structure we connect to collective intelligence (CI). Despite existing work, there is a lack of comprehensive reviews connecting the cortical column to the architectures of repeated neural modules. This review aims to fill that gap by synthesizing historical, theoretical, and methodological perspectives on neural module repetition. We distinguish between architectural repetition - reusing structure - and parameter-shared module repetition, where the same functional unit is repeated across a network. The latter exhibits key CI properties such as robustness, adaptability, and generalization. Evidence suggests that the repeated module tends to converge toward a generalist module: simple, flexible problem solvers capable of handling many roles in the ensemble. This generalist tendency may offer solutions to longstanding challenges in modern AI: improved energy efficiency during training through simplicity and scalability, and robust embodied control via generalization. While empirical results suggest such systems can generalize to out-of-distribution problems, theoretical results are still lacking. Overall, architectures featuring module repetition remain an emerging and unexplored architectural strategy, with significant untapped potential for both efficiency, robustness, and adaptiveness. We believe that a system that adopts the benefits of CI, while adhering to architectural and functional principles of the minicolumns, could challenge the modern AI problems of scalability, energy consumption, and democratization.

Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) are emerging as a powerful paradigm for solving complex, multifaceted problems. However, the potential of these systems is often constrained by the prevalent plan-and-execute framework, which suffers from critical limitations: rigid plan execution, static agent capabilities, and inefficient communication. These weaknesses hinder their adaptability and robustness in dynamic environments. This paper introduces Aime, a novel multi-agent framework designed to overcome these challenges through dynamic, reactive planning and execution. Aime replaces the conventional static workflow with a fluid and adaptive architecture. Its core innovations include: (1) a Dynamic Planner that continuously refines the overall strategy based on real-time execution feedback; (2) an Actor Factory that implements Dynamic Actor instantiation, assembling specialized agents on-demand with tailored tools and knowledge; and (3) a centralized Progress Management Module that serves as a single source of truth for coherent, system-wide state awareness. We empirically evaluated Aime on a diverse suite of benchmarks spanning general reasoning (GAIA), software engineering (SWE-bench Verified), and live web navigation (WebVoyager). The results demonstrate that Aime consistently outperforms even highly specialized state-of-the-art agents in their respective domains. Its superior adaptability and task success rate establish Aime as a more resilient and effective foundation for multi-agent collaboration.

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting, appending all past turns regardless of their relevance. This leads to unbounded memory growth, increased computational costs, and degraded reasoning performance on out-of-distribution input lengths. We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks. At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning. This state integrates prior memory with new observations from the environment while strategically discarding irrelevant or redundant information. To support training in more realistic and compositional settings, we propose a simple yet effective and scalable approach to constructing multi-turn environments by composing existing datasets into arbitrarily complex task sequences. Experiments across three domains, including internal retrieval QA, open-domain web QA, and multi-turn web shopping, show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task, and generalizes beyond the training horizon. Our results demonstrate the promise of reasoning-driven memory consolidation as a scalable alternative to existing solutions for training long-horizon interactive agents, where both efficiency and performance are optimized.

Coral Protocol is an open and decentralized collaboration infrastructure that enables communication, coordination, trust and payments for The Internet of Agents. It addresses the growing need for interoperability in a world where organizations are deploying multiple specialized AI agents that must work together across domains and vendors. As a foundational platform for multi-agent AI ecosystems, Coral establishes a common language and coordination framework allowing any agent to participate in complex workflows with others. Its design emphasizes broad compatibility, security, and vendor neutrality, ensuring that agent interactions are efficient and trustworthy. In particular, Coral introduces standardized messaging formats for agent communication, a modular coordination mechanism for orchestrating multi-agent tasks, and secure team formation capabilities for dynamically assembling trusted groups of agents. Together, these innovations position Coral Protocol as a cornerstone of the emerging "Internet of Agents," unlocking new levels of automation, collective intelligence, and business value through open agent collaboration.

The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues under normal and diseased conditions by employing data-driven approaches such as clustering and trajectory inference. However, these methods consider cells as independent data points of population distributions. With spatial transcriptomics, we can represent cellular organization, along with dynamic cell-cell interactions that lead to changes in cell state. Still, key computational advances are necessary to enable the data-driven learning of such complex interactive cellular dynamics. While agent-based modeling (ABM) provides a powerful framework, traditional approaches rely on handcrafted rules derived from domain knowledge rather than data-driven approaches. To address this, we introduce Spatio Temporal Agent-Based Graph Evolution Dynamics(STAGED) integrating ABM with deep learning to model intercellular communication, and its effect on the intracellular gene regulatory network. Using graph ODE networks (GDEs) with shared weights per cell type, our approach represents genes as vertices and interactions as directed edges, dynamically learning their strengths through a designed attention mechanism. Trained to match continuous trajectories of simulated as well as inferred trajectories from spatial transcriptomics data, the model captures both intercellular and intracellular interactions, enabling a more adaptive and accurate representation of cellular dynamics.

From assuming oversight for complex workflows, such as procurement or recruitment, to carrying out proactive cybersecurity checks or automating support, enterprises are abuzz at the potential use cases for agentic AI. According to one Capgemini survey, 50% of business executives are set to invest in and implement AI agents in their organizations in 2025, up from just 10% currently. Gartner has also forecast that 33% of enterprise software applications will incorporate agentic AI by 2028. For context, in 2024 that proportion was less than 1%. "It's creating such a buzz – software enthusiasts seeing the possibilities unlocked by LLMs, venture capitalists wanting to find the next big thing, companies trying to find the'killer app," says Matt McLarty, chief technology officer at Boomi.

The donation game is a well-established framework for studying the emergence and evolution of cooperation in multi-agent systems. The cooperative behavior can be influenced by the environmental noise in partially observable settings and by the decision-making strategies of agents, which may incorporate not only reputation but also traits such as generosity and forgiveness. Traditional simulations often assume fully random interactions, where cooperation is tested between randomly selected agent pairs. In this paper, we investigate cooperation dynamics using the concept of Stephen Wolfram's one-dimensional binary cellular automata. This approach allows us to explore how cooperation evolves when interactions are limited to neighboring agents. We define binary cellular automata rules that conform to the donation game mechanics. Additionally, we introduce models of perceptual and action noise, along with a mutation matrix governing the probabilistic evolution of agent strategies. Our empirical results demonstrate that cooperation is significantly affected by agents' mobility and their spatial locality on the game board. These findings highlight the importance of distinguishing between entirely random multi-agent systems and those in which agents are more likely to interact with their nearest neighbors.

In this paper, we introduce Hebbian learning as a novel method for swarm robotics, enabling the automatic emergence of heterogeneity. Hebbian learning presents a biologically inspired form of neural adaptation that solely relies on local information. By doing so, we resolve several major challenges for learning heterogeneous control: 1) Hebbian learning removes the complexity of attributing emergent phenomena to single agents through local learning rules, thus circumventing the micro-macro problem; 2) uniform Hebbian learning rules across all swarm members limit the number of parameters needed, mitigating the curse of dimensionality with scaling swarm sizes; and 3) evolving Hebbian learning rules based on swarm-level behaviour minimises the need for extensive prior knowledge typically required for optimising heterogeneous swarms. This work demonstrates that with Hebbian learning heterogeneity naturally emerges, resulting in swarm-level behavioural switching and in significantly improved swarm capabilities. It also demonstrates how the evolution of Hebbian learning rules can be a valid alternative to Multi Agent Reinforcement Learning in standard benchmarking tasks.