Online harms are a growing problem in digital spaces, putting user safety at risk and reducing trust in social media platforms. One of the most persistent forms of harm is hate speech. To address this, we need tools that combine the speed and scale of automated systems with the judgment and insight of human moderators. These tools should not only find harmful content but also explain their decisions clearly, helping to build trust and understanding. In this paper, we present WATCHED, a chatbot designed to support content moderators in tackling hate speech. The chatbot is built as an Artificial Intelligence Agent system that uses Large Language Models along with several specialised tools. It compares new posts with real examples of hate speech and neutral content, uses a BERT-based classifier to help flag harmful messages, looks up slang and informal language using sources like Urban Dictionary, generates chain-of-thought reasoning, and checks platform guidelines to explain and support its decisions. This combination allows the chatbot not only to detect hate speech but to explain why content is considered harmful, grounded in both precedent and policy. Experimental results show that our proposed method surpasses existing state-of-the-art methods, reaching a macro F1 score of 0.91. Designed for moderators, safety teams, and researchers, the tool helps reduce online harms by supporting collaboration between AI and human oversight.

We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic property from the current state of the system. Since computational efficiency is key to enable timely intervention against predicted violations, several state-of-the-art QPM approaches rely on fast machine-learning surrogates to provide prediction intervals for the satisfaction values, using conformal inference to offer statistical guarantees. However, these QPM methods suffer when the monitored agent exhibits multi-modal dynamics, whereby certain modes may yield high satisfaction values while others critically violate the property. Existing QPM methods are mode-agnostic and so would yield overly conservative and uninformative intervals that lack meaningful mode-specific satisfaction information. To address this problem, we present GenQPM, a method that leverages deep generative models, specifically score-based diffusion models, to reliably approximate the probabilistic and multi-modal system dynamics without requiring explicit model access. GenQPM employs a mode classifier to partition the predicted trajectories by dynamical mode. For each mode, we then apply conformal inference to produce statistically valid, mode-specific prediction intervals. We demonstrate the effectiveness of GenQPM on a benchmark of agent navigation and autonomous driving tasks, resulting in prediction intervals that are significantly more informative (less conservative) than mode-agnostic baselines.

Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we propose OpenMulti, an open-vocabulary instance-level multi-agent distributed implicit mapping framework. Specifically, we introduce a Cross-Agent Instance Alignment module, which constructs an Instance Collaborative Graph to ensure consistent instance understanding across agents. To alleviate the degradation of mapping accuracy due to the blind-zone optimization trap, we leverage Cross Rendering Supervision to enhance distributed learning of the scene. Experimental results show that OpenMulti outperforms related algorithms in both fine-grained geometric accuracy and zero-shot semantic accuracy. In addition, OpenMulti supports instance-level retrieval tasks, delivering semantic annotations for downstream applications. The project website of OpenMulti is publicly available at https://openmulti666.github.io/.

In the coming decade, artificially intelligent agents with the ability to plan and execute complex tasks over long time horizons with little direct oversight from humans may be deployed across the economy. This chapter surveys recent developments and highlights open questions for economists around how AI agents might interact with humans and with each other, shape markets and organizations, and what institutions might be required for well-functioning markets.

Multi-task learning is an effective way to address the challenge of model personalization caused by high data heterogeneity in federated learning. However, extending multi-task learning to the online decentralized federated learning setting is yet to be explored. The online decentralized federated learning setting considers many real-world applications of federated learning, such as autonomous systems, where clients communicate peer-to-peer and the data distribution of each client is time-varying. A more serious problem in real-world applications of federated learning is the presence of Byzantine clients. Byzantine-resilient approaches used in federated learning work only when the number of Byzantine clients is less than one-half the total number of clients. Yet, it is difficult to put a limit on the number of Byzantine clients within a system in reality. However, recent work in robotics shows that it is possible to exploit cyber-physical properties of a system to predict clients' behavior and assign a trust probability to received signals. This can help to achieve resiliency in the presence of a dominating number of Byzantine clients. Therefore, in this paper, we develop an online decentralized federated multi-task learning algorithm to provide model personalization and resiliency when the number of Byzantine clients dominates the number of honest clients. Our proposed algorithm leverages cyber-physical properties, such as the received signal strength in wireless systems or side information, to assign a trust probability to local models received from neighbors in each iteration. Our simulation results show that the proposed algorithm performs close to a Byzantine-free setting.

Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning and generation tasks. However, their proficiency in complex causal reasoning, discovery, and estimation remains an area of active development, often hindered by issues like hallucination, reliance on spurious correlations, and difficulties in handling nuanced, domain - specific, or personalized causal relationships. Multi - agent system s, leveraging the collaborative or specialized abilities of multiple LLM - based agents, are emerging as a powerful paradigm to address these limitations. This review paper explores the burgeoning field of causal multi - agent LLMs. We examine how these system s are designed to tackle different facets of causality, including causal reasoning and counterfactual analysis, causal discovery from data, and the estimation of causal effects. We delve into the diverse architectural patterns and interaction protocols emp loyed, from pipeline - based processing and debate frameworks to simulation environments and iterative refinement loops. Furthermore, we discuss the evaluation methodologies, benchmarks, and diverse application domains where causal multi - agent LLMs are makin g an impact, including scientific discovery, healthcare, fact - checking, and personalized systems. Finally, we highlight the persistent challenges, open research questions, and promising future directions in this synergistic field, aiming to provide a compr ehensive overview of its current state and potential trajectory. 1. Introduction

Controller synthesis is a theoretical approach to the systematic design of discrete event systems. It constructs a controller to provide feedback and control to the system, ensuring it meets specified control specifications. Traditional controller synthesis methods often use formal languages to describe control specifications and are mainly oriented towards single-agent and non-probabilistic systems. With the increasing complexity of systems, the control requirements that need to be satisfied also become more complex. Based on this, this paper proposes a controller synthesis method for semi-cooperative semi-competitive multi-agent probabilistic discrete event systems to solve the controller synthesis problem based on temporal logic specifications. The controller can ensure the satisfaction of specifications to a certain extent. The specification is given in the form of a linear temporal logic formula. This paper designs a controller synthesis algorithm that combines probabilistic model checking. Finally, the effectiveness of this method is verified through a case study.

Abstract-- This paper investigates a passivity-based approach to output consensus analysis in heterogeneous networks com - posed of non-identical agents coupled via nonlinear intera ctions, in the presence of measurement and/or communication noise. Focusing on agents that are input-feedforward passive (IFP), we first examine whether a shortage of passivity in some agents can be compensated by a passivity surplus in others, in the sense of preserving the passivity of the transformed open-l oop system defined by the agent dynamics and network topology. We show that such compensation is only feasible when at most one agent lacks passivity, and we characterise how this defic it can be offset using the excess passivity within the group of agents. For general networks, we then investigate passivit y compensation within the feedback interconnection by lever aging the passivity surplus in the coupling links to locally compe nsate for the lack of passivity in the adjacent agents. In particul ar, a distributed condition, expressed in terms of passivity in dices and coupling gains, is derived to ensure output consensus of the interconnected network.

Cybersecurity defense involves interactions between adversarial parties (namely defenders and hackers), making multi-agent reinforcement learning (MARL) an ideal approach for modeling and learning strategies for these scenarios. This paper addresses one of the key challenges to MARL, the complexity of simultaneous training of agents in nontrivial environments, and presents a novel policy-based Nash Q-learning to directly converge onto a steady equilibrium. We demonstrate the successful implementation of this algorithm in a notable complex cyber defense simulation treated as a two-player zero-sum Markov game setting. We propose the Nash Q-Network, which aims to learn Nash-optimal strategies that translate to robust defenses in cybersecurity settings. Our approach incorporates aspects of proximal policy optimization (PPO), deep Q-network (DQN), and the Nash-Q algorithm, addressing common challenges like non-stationarity and instability in multi-agent learning. The training process employs distributed data collection and carefully designed neural architectures for both agents and critics.

Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited information. In contrast, AI systems struggle to automatically structure and reason about these implicit social contexts. In this paper, we introduce a novel structured social world representation formalism (S3AP), designed to help AI systems reason more effectively about social dynamics. Following a POMDP-driven design, S3AP represents social interactions as structured tuples, such as state, observation, agent actions, and mental states, which can be automatically induced from free-form narratives or other inputs. We first show S3AP can help LLMs better understand social narratives across 5 social reasoning tasks (e.g., +51% improvement on FANToM's theory-of-mind reasoning with OpenAI's o1), reaching new state-of-the-art (SOTA) performance. We then induce social world models from these structured representations, demonstrating their ability to predict future social dynamics and improve agent decision-making, yielding up to +18% improvement on the SOTOPIA social interaction benchmark. Our findings highlight the promise of S3AP as a powerful, general-purpose representation for social world states, enabling the development of more socially-aware systems that better navigate social interactions.