Large Language Models (LLMs) have demonstrated significant potential in causal discovery tasks by utilizing their vast expert knowledge from extensive text corpora. However, the multi-agent capabilities of LLMs in causal discovery remain underexplored. This paper introduces a general framework to investigate this potential. The first is the Meta Agents Model, which relies exclusively on reasoning and discussions among LLM agents to conduct causal discovery. The second is the Coding Agents Model, which leverages the agents' ability to plan, write, and execute code, utilizing advanced statistical libraries for causal discovery. The third is the Hybrid Model, which integrates both the Meta Agents Model and Coding Agents Model approaches, combining the statistical analysis and reasoning skills of multiple agents. Our proposed framework shows promising results by effectively utilizing LLMs' expert knowledge, reasoning capabilities, multi-agent cooperation, and statistical causal methods. By exploring the multi-agent potential of LLMs, we aim to establish a foundation for further research in utilizing LLMs multi-agent for solving causal-related problems.

We study a collaborative learning problem where $m$ agents estimate a vector $\mu\in\mathbb{R}^d$ by collecting samples from normal distributions, with each agent $i$ incurring a cost $c_{i,k} \in (0, \infty]$ to sample from the $k^{\text{th}}$ distribution $\mathcal{N}(\mu_k, \sigma^2)$. Instead of working on their own, agents can collect data that is cheap to them, and share it with others in exchange for data that is expensive or even inaccessible to them, thereby simultaneously reducing data collection costs and estimation error. However, when agents have different collection costs, we need to first decide how to fairly divide the work of data collection so as to benefit all agents. Moreover, in naive sharing protocols, strategic agents may under-collect and/or fabricate data, leading to socially undesirable outcomes. Our mechanism addresses these challenges by combining ideas from cooperative and non-cooperative game theory. We use ideas from axiomatic bargaining to divide the cost of data collection. Given such a solution, we develop a Nash incentive-compatible (NIC) mechanism to enforce truthful reporting. We achieve a $\mathcal{O}(\sqrt{m})$ approximation to the minimum social penalty (sum of agent estimation errors and data collection costs) in the worst case, and a $\mathcal{O}(1)$ approximation under favorable conditions. We complement this with a hardness result, showing that $\Omega(\sqrt{m})$ is unavoidable in any NIC mechanism.

Contemporary artificial intelligence systems are pivotal in enhancing human efficiency and safety across various domains. One such domain is autonomous systems, especially in automotive and defense use cases. Artificial intelligence brings learning and enhanced decision-making to autonomy system goal-oriented behaviors and human independence. However, the lack of clear understanding of autonomy system capabilities hampers human-machine or machine-machine interaction and interdiction. This necessitates varying degrees of human involvement for safety, accountability, and explainability purposes. Yet, measuring the level autonomous capability in an autonomous system presents a challenge. Two scales of measurement exist, yet measuring autonomy presupposes a variety of elements not available in the wild. This is why existing measures for level of autonomy are operationalized only during design or test and evaluation phases. No measure for level of autonomy based on observed system behavior exists at this time. To address this, we outline a potential measure for predicting level of autonomy using observable actions. We also present an algorithm incorporating the proposed measure. The measure and algorithm have significance to researchers and practitioners interested in a method to blind compare autonomous systems at runtime. Defense-based implementations are likewise possible because counter-autonomy depends on robust identification of autonomous systems.

Multi-agent reinforcement learning (MARL) has recently excelled in solving challenging cooperative and competitive multi-agent problems in various environments with, mostly, few agents and full observability. Moreover, a range of crucial robotics-related tasks, such as multi-robot navigation and obstacle avoidance, that have been conventionally approached with the classical non-learnable methods (e.g., heuristic search) is currently suggested to be solved by the learning-based or hybrid methods. Still, in this domain, it is hard, not to say impossible, to conduct a fair comparison between classical, learning-based, and hybrid approaches due to the lack of a unified framework that supports both learning and evaluation. To this end, we introduce POGEMA, a set of comprehensive tools that includes a fast environment for learning, a generator of problem instances, the collection of pre-defined ones, a visualization toolkit, and a benchmarking tool that allows automated evaluation. We introduce and specify an evaluation protocol defining a range of domain-related metrics computed on the basics of the primary evaluation indicators (such as success rate and path length), allowing a fair multi-fold comparison. The results of such a comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented.

One effective way to optimize the offloading process is by minimizing the transmission time. This is particularly true in a Vehicular Adhoc Network (VANET) where vehicles frequently download and upload High-definition (HD) map data which requires constant updates. This implies that latency and throughput requirements must be guaranteed by the wireless system. To achieve this, adjustable contention windows (CW) allocation strategies in the standard IEEE802.11p have been explored by numerous researchers. Nevertheless, their implementations demand alterations to the existing standard which is not always desirable. To address this issue, we proposed a Q-Learning algorithm that operates at the application layer. Moreover, it could be deployed in any wireless network thereby mitigating the compatibility issues. The solution has demonstrated a better network performance with relatively fewer optimization requirements as compared to the Deep Q Network (DQN) and Actor-Critic algorithms. The same is observed while evaluating the model in a multi-agent setup showing higher performance compared to the single-agent setup.

Social rewards shape human behavior. During development, a caregiver guides a learner's behavior towards culturally aligned goals and values. How do these behaviors persist and generalize when the caregiver is no longer present, and the learner must continue autonomously? Here, we propose a model of value internalization where social feedback trains an internal social reward (ISR) model that generates internal rewards when social rewards are unavailable. Through empirical simulations, we show that an ISR model prevents agents from unlearning socialized behaviors and enables generalization in out-of-distribution tasks. We characterize the implications of incomplete internalization, akin to "reward hacking" on the ISR. Additionally, we show that our model internalizes prosocial behavior in a multi-agent environment. Our work provides a foundation for understanding how humans acquire and generalize values and offers insights for aligning AI with human values.

In the field of modern robotics, robots are proving to be useful in tackling high-risk situations, such as navigating hazardous environments like burning buildings, earthquake-stricken areas, or patrolling crime-ridden streets, as well as exploring uncharted caves. These scenarios share similarities with maze exploration problems in terms of complexity. While several methods have been proposed for single-agent systems, ranging from potential fields to flood-fill methods, recent research endeavors have focused on creating methods tailored for multiple agents to enhance the quality and efficiency of maze coverage. The contribution of this paper is the implementation of established maze exploration methods and their comparison with a new cost-utility algorithm designed for multiple agents, which combines the existing methodologies to optimize exploration outcomes. Through a comprehensive and comparative analysis, this paper evaluates the performance of the new approach against the implemented baseline methods from the literature, highlighting its efficacy and potential advantages in various scenarios. The code and experimental results supporting this study are available in the following repository (https://github.com/manouslinard/multiagent-exploration/).

In the dynamic landscape of technology, the convergence of Artificial Intelligence (AI) and Operating Systems (OS) has emerged as a pivotal arena for innovation. Our exploration focuses on the symbiotic relationship between AI and OS, emphasizing how AI-driven tools enhance OS performance, security, and efficiency, while OS advancements facilitate more sophisticated AI applications. We delve into various AI techniques employed to optimize OS functionalities, including memory management, process scheduling, and intrusion detection. Simultaneously, we analyze the role of OS in providing essential services and infrastructure that enable effective AI application execution, from resource allocation to data processing. The article also addresses challenges and future directions in this domain, emphasizing the imperative of secure and efficient AI integration within OS frameworks. By examining case studies and recent developments, our review provides a comprehensive overview of the current state of AI-OS integration, underscoring its significance in shaping the next generation of computing technologies. Finally, we explore the promising prospects of Intelligent OSes, considering not only how innovative OS architectures will pave the way for groundbreaking opportunities but also how AI will significantly contribute to advancing these next-generation OSs.

As the complexities of Dynamic Data Driven Applications Systems increase, preserving their resilience becomes more challenging. For instance, maintaining power grid resilience is becoming increasingly complicated due to the growing number of stochastic variables (such as renewable outputs) and extreme weather events that add uncertainty to the grid. Current optimization methods have struggled to accommodate this rise in complexity. This has fueled the growing interest in data-driven methods used to operate the grid, leading to more vulnerability to cyberattacks. One such disruption that is commonly discussed is the adversarial disruption, where the intruder attempts to add a small perturbation to input data in order to "manipulate" the system operation. During the last few years, work on adversarial training and disruptions on the power system has gained popularity. In this paper, we will first review these applications, specifically on the most common types of adversarial disruptions: evasion and poisoning disruptions. Through this review, we highlight the gap between poisoning and evasion research when applied to the power grid. This is due to the underlying assumption that model training is secure, leading to evasion disruptions being the primary type of studied disruption. Finally, we will examine the impacts of data poisoning interventions and showcase how they can endanger power grid resilience.

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the complexity of driving tasks often necessitates the collaboration of multiple, heterogeneous agents, underscoring the need for such LLM-driven agents to engage in cooperative knowledge sharing and cognitive synergy. Despite the promise of LLMs, current applications predominantly center around single agent scenarios. To broaden the horizons of knowledge-driven strategies and bolster the generalization capabilities of autonomous agents, we propose the KoMA framework consisting of multi-agent interaction, multi-step planning, shared-memory, and ranking-based reflection modules to enhance multi-agents' decision-making in complex driving scenarios. Based on the framework's generated text descriptions of driving scenarios, the multi-agent interaction module enables LLM agents to analyze and infer the intentions of surrounding vehicles, akin to human cognition. The multi-step planning module enables LLM agents to analyze and obtain final action decisions layer by layer to ensure consistent goals for short-term action decisions. The shared memory module can accumulate collective experience to make superior decisions, and the ranking-based reflection module can evaluate and improve agent behavior with the aim of enhancing driving safety and efficiency. The KoMA framework not only enhances the robustness and adaptability of autonomous driving agents but also significantly elevates their generalization capabilities across diverse scenarios. Empirical results demonstrate the superiority of our approach over traditional methods, particularly in its ability to handle complex, unpredictable driving environments without extensive retraining.