Learning safe reinforcement learning (RL) policies from offline multi-task datasets without direct environmental interaction is crucial for efficient and reliable deployment of RL agents. Benefiting from their scalability and strong in-context learning capabilities, recent approaches attempt to utilize Decision Transformer (DT) architectures for offline safe RL, demonstrating promising adaptability across varying safety budgets. However, these methods primarily focus on single-constraint scenarios and struggle with diverse constraint configurations across multiple tasks. Additionally, their reliance on heuristically defined Return-To-Go (RTG) inputs limits flexibility and reduces learning efficiency, particularly in complex multi-task scenarios. To address these limitations, we propose CoPDT, a novel DT-based framework designed to enhance adaptability to diverse constraints (i.e., cost functions) and varying budgets. Specifically, CoPDT introduces a constraint prioritized prompt encoder, which leverages sparse binary cost signals to accurately identify constraints, and a constraint prioritized Return-To-Go (CPRTG) token mechanism, which dynamically generates RTGs based on identified constraints and corresponding safety budgets. Extensive experiments on the OSRL benchmark demonstrate that CoPDT achieves superior efficiency and significantly enhanced safety compliance across diverse multi-task scenarios, surpassing state-of-the-art DT-based methods by satisfying safety constraints in more than twice as many tasks.

AI is making journalistic language more repetitive and predictable - and it's a problem for all of us What happens to language when a growing amount of text published in the press, online and on social media is written by machines? This question is not just important for the profession of journalism - it also has an impact on the richness of the language we all use to comprehend, describe and discuss reality itself. Historically, the press has been a space where public language grows and becomes richer. It is not, of course, the only driver of linguistic change, but it is one of the fields where new or emerging words, turns of phrase and ways of describing facts begin to circulate within society. Studies on journalistic language and neologisms clearly demonstrate that newspapers are platforms for the creation and dissemination of new vocabulary, especially when it is needed to report on events, technology and social changes for a broad audience.

We investigate various stochastic bandit problems in the presence of adversarial corruptions. A seminal work for this problem is the BARBAR [1] algorithm, which achieves both robustness and efficiency. However, it suffers from a regret of O(KC), which does not match the lower bound of Ω(C), where K denotes the number of arms and C denotes the corruption level. In this paper, we first improve the BARBAR algorithm by proposing a novel framework called BARBAT, which eliminates the factor of K to achieve an optimal regret bound up to a logarithmic factor. We also extend BARBAT to various settings, including multi-agent bandits, graph bandits, combinatorial semi-bandits and batched bandits. Compared with the Follow-the-Regularized-Leader framework, our methods are more amenable to parallelization, making them suitable for multi-agent and batched bandit settings, and they incur lower computational costs, particularly in semi-bandit problems. Numerical experiments verify the efficiency of the proposed methods.

T The struggle raditional study to of modeling capture social the emer approaches, div gence ersity has and such long comple as rule-based been xity a of central Agent-Based human focus beha in vior Models social, particularly (ABMs), science.

Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the growing integration of LLMs and AI agents with external information sources and real-world environments raises critical questions about how they engage with and are influenced by these external data sources and interactive contexts. This study investigates how expanding retrieval access--from no external sources to Wikipedia-based retrieval and open web search--affects model reliability, bias propagation, and harmful content generation. Through extensive benchmarking of censored and uncensored LLMs and AIAgents, our findings reveal a consistent degradation in refusal rates, bias sensitivity, and harmfulness safeguards as models gain broader access to external sources, culminating in a phenomenon we term safety degradation. Notably, retrieval-enabled agents built on aligned LLMs often behave more unsafely than uncensored models without retrieval. This effect persists even under strong retrieval accuracy and prompt-based mitigation, suggesting that the mere presence of retrieved content reshapes model behavior in structurally unsafe ways. These findings underscore the need for robust mitigation strategies to ensure fairness and reliability in retrieval-enabled and increasingly autonomous AI systems. Content Warning: This paper contains examples of harmful language.

Appendix A describes the Unity-based interface implemented in EVAAA, including an environment setup, prefab structures, and object instantiation. Appendix B provides a comprehensive introduction to Essential Variables (EVs), including their design, dynamics, and role in internal state regulation. Appendix C explains the implementation of the reward system and its connection to the balance of internal states. Appendix E outlines the modular configuration to generate EVAAA environments, along with the instructions for environment customization. Appendix F presents the structure and progression of naturalistic training environments. Appendix G describes the design of unseen experimental testbeds for evaluation. Appendix I provides analyses of agent behavior across training and test environments, including emergent behavioral patterns. All code and data are publicly available at: https://github.com/cocoanlab/evaaa A.1 Prefabs Environmental elements such as terrain, resources, obstacles, and predators are implemented as reusable and configurable Unity prefabs. Prefabs are grouped into Agents, Environment, and Materials. Each category includes reusable components for constructing and customizing interactive scenes: Agents (main agent and predators), Environment (terrain and containers), and Materials (varied textures and colors for visual distinction). This modular system enables rapid prototyping, task generation, condition randomization, and reproducible scene setup. Prefabs can be customized through the Unity Editor or programmatically at runtime, and reused across scenes without manual rebuilding.

In cooperative Multi-Agent Reinforcement Learning (MARL), agents that share policy network parameters often learn similar behaviors, which hinders effective exploration and can lead to suboptimal cooperative policies. Recent advances have attempted to promote multi-agent diversity by leveraging the Wasserstein distance to increase policy differences. However, these methods cannot effectively encourage diverse policies due to ineffective Wasserstein distance caused by the policy similarity. To address this limitation, we propose Wasserstein Contrastive Diversity (WCD) exploration, a novel approach that promotes multi-agent diversity by maximizing the Wasserstein distance between the trajectory distributions of different agents in a latent representation space. To make the Wasserstein distance meaningful, we propose a novel next-step prediction method based on Contrastive Predictive Coding (CPC) to learn distinguishable trajectory representations. Additionally, we introduce an optimized kernel-based method to compute the Wasserstein distance more efficiently. Since the Wasserstein distance is inherently defined for two distributions, we extend it to support multiple agents, enabling diverse policy learning. Empirical evaluations across a variety of challenging multi-agent tasks demonstrate that WCD outperforms existing state-of-the-art methods, delivering superior performance and enhanced exploration.

Graphs in the real world are fragmented and dynamic, lacking collaboration akin to that observed in human societies.

Offline Learning from Observation (LfO) focuses on enabling agents to imitate expert behavior using datasets that contain only expert state trajectories and separate transition data with suboptimal actions. This setting is both practical and critical in real-world scenarios where direct environment interaction or access to expert action labels is costly, risky, or infeasible. Most existing LfO methods attempt to solve this problem through state or state-action occupancy matching. They typically rely on pretraining a discriminator to differentiate between expert and non-expert states, which could introduce errors and instability--especially when the discriminator is poorly trained. While recent discriminator-free methods have emerged, they generally require substantially more data, limiting their practicality in low-data regimes.

We study fundamental connections between coalition formation games and clustering, illustrating the cross-disciplinary relevance of these concepts. We focus on graphical hedonic games where agents' preferences are compactly represented by a friendship graph and an enmity graph. In the context of clustering, friendship relations naturally align with data point similarities, whereas enmity corresponds to dissimilarities. We consider two stability notions based on single-agent deviations: local popularity and local stability.