For multi-agent reinforcement learning systems (MARLS), the problem formulation generally involves investing massive reward engineering effort specific to a given problem. However, this effort often cannot be translated to other problems; worse, it gets wasted when system dynamics change drastically. This problem is further exacerbated in sparse reward scenarios, where a meaningful heuristic can assist in the policy convergence task. We propose GOVerned Reward Engineering Kernels (GOV-REK), which dynamically assign reward distributions to agents in MARLS during its learning stage. We also introduce governance kernels, which exploit the underlying structure in either state or joint action space for assigning meaningful agent reward distributions. During the agent learning stage, it iteratively explores different reward distribution configurations with a Hyperband-like algorithm to learn ideal agent reward models in a problem-agnostic manner. Our experiments demonstrate that our meaningful reward priors robustly jumpstart the learning process for effectively learning different MARL problems.

In recent years, deep or reinforcement learning approaches have been applied to optimise investment portfolios through learning the spatial and temporal information under the dynamic financial market. Yet in most cases, the existing approaches may produce biased trading signals based on the conventional price data due to a lot of market noises, which possibly fails to balance the investment returns and risks. Accordingly, a multi-agent and self-adaptive portfolio optimisation framework integrated with attention mechanisms and time series, namely the MASAAT, is proposed in this work in which multiple trading agents are created to observe and analyse the price series and directional change data that recognises the significant changes of asset prices at different levels of granularity for enhancing the signal-to-noise ratio of price series. Afterwards, by reconstructing the tokens of financial data in a sequence, the attention-based cross-sectional analysis module and temporal analysis module of each agent can effectively capture the correlations between assets and the dependencies between time points. Besides, a portfolio generator is integrated into the proposed framework to fuse the spatial-temporal information and then summarise the portfolios suggested by all trading agents to produce a newly ensemble portfolio for reducing biased trading actions and balancing the overall returns and risks. The experimental results clearly demonstrate that the MASAAT framework achieves impressive enhancement when compared with many well-known portfolio optimsation approaches on three challenging data sets of DJIA, S&P 500 and CSI 300. More importantly, our proposal has potential strengths in many possible applications for future study.

Current trust and reputation models continue to have significant limitations, such as the inability to deal with agents constantly entering or exiting open multi-agent systems (open MAS), as well as continuously changing behaviors. Our study is based on CA, a previously proposed decentralized computational trust model from the trustee's point of view, inspired by synaptic plasticity and the formation of assemblies in the human brain. It is designed to meet the requirements of highly dynamic and open MAS, and its main difference with most conventional trust and reputation models is that the trustor does not select a trustee to delegate a task; instead, the trustee determines whether it is qualified to successfully execute it. We ran a series of simulations to compare CA model to FIRE, a well-established, decentralized trust and reputation model for open MAS under conditions of continuous trustee and trustor population replacement, as well as continuous change of trustees' abilities to perform tasks. The main finding is that FIRE is superior to changes in the trustee population, whereas CA is resilient to the trustor population changes. When the trustees switch performance profiles FIRE clearly outperforms despite the fact that both models' performances are significantly impacted by this environmental change. Findings lead us to conclude that learning to use the appropriate trust model, according to the dynamic conditions in effect could maximize the trustor's benefits.

Despite the significant demand for assistive technology among vulnerable groups (e.g., the elderly, children, and the disabled) in daily tasks, research into advanced AI-driven assistive solutions that genuinely accommodate their diverse needs remains sparse. Traditional human-machine interaction tasks often require machines to simply help without nuanced consideration of human abilities and feelings, such as their opportunity for practice and learning, sense of self-improvement, and self-esteem. Addressing this gap, we define a pivotal and novel challenge Smart Help, which aims to provide proactive yet adaptive support to human agents with diverse disabilities and dynamic goals in various tasks and environments. To establish this challenge, we leverage AI2-THOR to build a new interactive 3D realistic household environment for the Smart Help task. We introduce an innovative opponent modeling module that provides a nuanced understanding of the main agent's capabilities and goals, in order to optimize the assisting agent's helping policy. Rigorous experiments validate the efficacy of our model components and show the superiority of our holistic approach against established baselines. Our findings illustrate the potential of AI-imbued assistive robots in improving the well-being of vulnerable groups.

Robot swarms can effectively serve a variety of sensing and inspection applications. Certain inspection tasks require a binary classification decision. This work presents an experimental setup for a surface inspection task based on vibration sensing and studies a Bayesian two-outcome decision-making algorithm in a swarm of miniaturized wheeled robots. The robots are tasked with individually inspecting and collectively classifying a 1mx1m tiled surface consisting of vibrating and non-vibrating tiles based on the majority type of tiles. The robots sense vibrations using onboard IMUs and perform collision avoidance using a set of IR sensors. We develop a simulation and optimization framework leveraging the Webots robotic simulator and a Particle Swarm Optimization (PSO) method. We consider two existing information sharing strategies and propose a new one that allows the swarm to rapidly reach accurate classification decisions. We first find optimal parameters that allow efficient sampling in simulation and then evaluate our proposed strategy against the two existing ones using 100 randomized simulation and 10 real experiments. We find that our proposed method compels the swarm to make decisions at an accelerated rate, with an improvement of up to 20.52% in mean decision time at only 0.78% loss in accuracy.

The emergent large language/multimodal models facilitate the evolution of mobile agents, especially in the task of mobile UI automation. However, existing evaluation approaches, which rely on human validation or established datasets to compare agent-predicted actions with predefined ones, are unscalable and unfaithful. To overcome these limitations, this paper presents LlamaTouch, a testbed for on-device agent execution and faithful, scalable agent evaluation. By observing that the task execution process only transfers UI states, LlamaTouch employs a novel evaluation approach that only assesses whether an agent traverses all manually annotated, essential application/system states. LlamaTouch comprises three key techniques: (1) On-device task execution that enables mobile agents to interact with real mobile environments for task completion. (2) Fine-grained UI component annotation that merges pixel-level screenshots and textual screen hierarchies to explicitly identify and precisely annotate essential UI components with a rich set of designed annotation primitives. (3) A multi-level state matching algorithm that utilizes exact and fuzzy matching to accurately detect critical information in each screen with unpredictable UI layout/content dynamics. LlamaTouch currently incorporates four mobile agents and 495 UI automation tasks, encompassing both tasks in the widely-used datasets and our self-constructed ones for more diverse mobile applications. Evaluation results demonstrate the LlamaTouch's high faithfulness of evaluation in real environments and its better scalability than human validation. LlamaTouch also enables easy task annotation and integration of new mobile agents. Code and dataset are publicly available at https://github.com/LlamaTouch/LlamaTouch.

In the rapidly evolving field of artificial intelligence, the ability to harness and integrate knowledge across various domains stands as a paramount challenge and opportunity. This study introduces a novel approach to cross-domain knowledge discovery through the deployment of multi-AI agents, each specialized in distinct knowledge domains. These AI agents, designed to function as domain-specific experts, collaborate in a unified framework to synthesize and provide comprehensive insights that transcend the limitations of single-domain expertise. By facilitating seamless interaction among these agents, our platform aims to leverage the unique strengths and perspectives of each, thereby enhancing the process of knowledge discovery and decision-making. We present a comparative analysis of the different multi-agent workflow scenarios evaluating their performance in terms of efficiency, accuracy, and the breadth of knowledge integration. Through a series of experiments involving complex, interdisciplinary queries, our findings demonstrate the superior capability of domain specific multi-AI agent system in identifying and bridging knowledge gaps. This research not only underscores the significance of collaborative AI in driving innovation but also sets the stage for future advancements in AI-driven, cross-disciplinary research and application. Our methods were evaluated on a small pilot data and it showed a trend we expected, if we increase the amount of data we custom train the agents, the trend is expected to be more smooth.

Abstract---Defenders are overwhelmed by the number and scale of attacks against their networks.This problem will only be exacerbated as attackers leverage artificial intelligence to automate their workflows. We propose a path to autonomous cyber agents able to augment defenders by automating critical steps in the cyber defense life cycle. To avoid being overwhelmed, and complexity. The deep neural nets in order to generalize well across creation of autonomous cyber defense agents is one states. By leveraging deep RL, DeepMind has trained promising approach to automate operations and prevent reinforcement learning algorithms to defeat expert human cyber defenders from being overwhelmed.

Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing demonstrations and user feedback for personalization. However, personal preferences are subject to change and might even be context-dependent. Yet traditional reinforcement learning (RL) approaches with a static reward function often fall short in adapting to these varying user preferences. This paper introduces a framework that combines multi-objective reinforcement learning (MORL) with demonstration-based learning. Our approach allows for dynamic adaptation to changing user preferences without retraining. Through rigorous evaluations, including sim-to-real and robot-to-robot transfers, we demonstrate our framework's capability to reflect user preferences accurately while achieving high navigational performance in terms of collision avoidance and goal pursuance.

This paper introduces a novel zero-shot motion planning method that allows users to quickly design smooth robot motions in Cartesian space. A B\'ezier curve-based Cartesian plan is transformed into a joint space trajectory by our neuro-inspired inverse kinematics (IK) method CycleIK, for which we enable platform independence by scaling it to arbitrary robot designs. The motion planner is evaluated on the physical hardware of the two humanoid robots NICO and NICOL in a human-in-the-loop grasping scenario. Our method is deployed with an embodied agent that is a large language model (LLM) at its core. We generalize the embodied agent, that was introduced for NICOL, to also be embodied by NICO. The agent can execute a discrete set of physical actions and allows the user to verbally instruct various different robots. We contribute a grasping primitive to its action space that allows for precise manipulation of household objects. The new CycleIK method is compared to popular numerical IK solvers and state-of-the-art neural IK methods in simulation and is shown to be competitive with or outperform all evaluated methods when the algorithm runtime is very short. The grasping primitive is evaluated on both NICOL and NICO robots with a reported grasp success of 72% to 82% for each robot, respectively.