This is not a typical survey of world models; it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a "world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass loosely related branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards true world models. The term world model has been used to describe many different ideas: learned environment simulators for reinforcement learning (Ha & Schmidhuber, 2018; Hafner et al., 2019), agents that integrate learned models with planning (Schrittwieser et al., 2020), and large language models that simulate entire societies (Park et al., 2023). Y et despite hundreds of related works, there is no clear consensus on how to actually build a true world model. In this paper, we take a stance: the path is much narrower than it appears. A true world model is not a monolithic entity but a system synthesized from three core subsystems: a generative heart that produces world states, an interactive loop that closes the action-perception cycle in real time, and a persistent memory system that sustains coherence over long horizons. The history of the field can be understood as an evolutionary journey from first mastering these components in isolation to now integrating them. Most works focus on optimizing narrow tasks and drift away from the generative, interactive, and persistent nature required for a true world model. To make this perspective concrete, we chart the historical evolution of world models as a sequence of five stages, shown in Figure 1. It begins with Stage I: Mask-based Models, which established a universal, token-based pretraining paradigm across modalities.

Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging predefined signatures and static heuristics to identify and block malicious traffic. However, the emergence of AI-driven techniques presents new challenges to SDN security, potentially compromising the efficacy of existing defence mechanisms. In this paper, we introduce~AdaDoS, an adaptive attack model that disrupt network operations while evading detection by existing DoS-based detectors through adversarial reinforcement learning (RL). Specifically, AdaDoS models the problem as a competitive game between an attacker, whose goal is to obstruct network traffic without being detected, and a detector, which aims to identify malicious traffic. AdaDoS can solve this game by dynamically adjusting its attack strategy based on feedback from the SDN and the detector. Additionally, recognising that attackers typically have less information than defenders, AdaDoS formulates the DoS-like attack as a partially observed Markov decision process (POMDP), with the attacker having access only to delay information between attacker and victim nodes. We address this challenge with a novel reciprocal learning module, where the student agent, with limited observations, enhances its performance by learning from the teacher agent, who has full observational capabilities in the SDN environment. AdaDoS represents the first application of RL to develop DoS-like attack sequences, capable of adaptively evading both machine learning-based and rule-based DoS-like attack detectors.

With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research. Especially in the face of adversarial attacks, DRL may suffer serious performance degradation or even make potentially dangerous decisions, so it is crucial to ensure their stability in security-sensitive scenarios. In this paper, we first introduce the basic framework of DRL and analyze the main security challenges faced in complex and changing environments. In addition, this paper proposes an adversarial attack classification framework based on perturbation type and attack target and reviews the mainstream adversarial attack methods against DRL in detail, including various attack methods such as perturbation state space, action space, reward function and model space. To effectively counter the attacks, this paper systematically summarizes various current robustness training strategies, including adversarial training, competitive training, robust learning, adversarial detection, defense distillation and other related defense techniques, we also discuss the advantages and shortcomings of these methods in improving the robustness of DRL. Finally, this paper looks into the future research direction of DRL in adversarial environments, emphasizing the research needs in terms of improving generalization, reducing computational complexity, and enhancing scalability and explainability, aiming to provide valuable references and directions for researchers.

The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.

Although quantum systems are generally described by quantum state vectors, we show that in certain cases their measurement processes can be reformulated as probabilistic equations expressed in terms of probabilistic state vectors. These probabilistic representations can, in turn, be approximated by the neural network dynamics of the Tensor Brain (TB) model. The Tensor Brain is a recently proposed framework for modeling perception and memory in the brain, providing a biologically inspired mechanism for efficiently integrating generated symbolic representations into reasoning processes.

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of robustness, which ensures stability under uncertainties, and resilience, the ability to recover from disruptions--a concept extensively studied in control systems but largely overlooked in MARL. In this paper, we present a large-scale empirical study comprising over 82,620 experiments to evaluate cooperation, robustness, and resilience in MARL across 4 real-world environments, 13 uncertainty types, and 15 hyperparameters. Our key findings are: (1) Under mild uncertainty, optimizing cooperation improves robustness and resilience, but this link weakens as perturbations intensify. Robustness and resilience also varies by algorithm and uncertainty type. (2) Robustness and resilience do not generalize across uncertainty modalities or agent scopes: policies robust to action noise for all agents may fail under observation noise on a single agent. (3) Hyperparameter tuning is critical for trustworthy MARL: surprisingly, standard practices like parameter sharing, GAE, and PopArt can hurt robustness, while early stopping, high critic learning rates, and Leaky ReLU consistently help. By optimizing hyperparameters only, we observe substantial improvement in cooperation, robustness and resilience across all MARL backbones, with the phenomenon also generalizing to robust MARL methods across these backbones. Code and results available at https://github.com/BUAA-TrustworthyMARL/adv_marl_benchmark .

In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability and communication constraints. We propose a decentralized framework in which each agent solves a constrained Markov decision process (CMDP), coordinating implicitly through a shared constraint vector. For the specific case of offloading, e.g., constraints prevent overloading shared server resources. Coordination constraints are updated infrequently and act as a lightweight coordination mechanism. They enable agents to align with global resource usage objectives but require little direct communication. Using safe reinforcement learning, agents learn policies that meet both local and global goals. We establish theoretical guarantees under mild assumptions and validate our approach experimentally, showing improved performance over centralized and independent baselines, especially in large-scale settings.

LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these challenges through the lens of agents' memory utilization along two critical dimensions: object semantics (identifying objects based on personal meaning) and user patterns (recalling sequences from behavioral routines). To assess these capabilities, we construct MEMENTO, an end-to-end two-stage evaluation framework comprising single-memory and joint-memory tasks. Our experiments reveal that current agents can recall simple object semantics but struggle to apply sequential user patterns to planning. Through in-depth analysis, we identify two critical bottlenecks: information overload and coordination failures when handling multiple memories. Based on these findings, we explore memory architectural approaches to address these challenges. Given our observation that episodic memory provides both personalized knowledge and in-context learning benefits, we design a hierarchical knowledge graph-based user-profile memory module that separately manages personalized knowledge, achieving substantial improvements on both single and joint-memory tasks. Project website: https://connoriginal.github.io/MEMENTO

Dynamic treatment regimes are sequential decision rules that adapt treatment according to individual time-varying characteristics and outcomes to achieve optimal effects, with applications in precision medicine, personalized recommendations, and dynamic marketing. Estimating optimal dynamic treatment regimes via sequential randomized trials might face costly and ethical hurdles, often necessitating the use of historical observational data. In this work, we utilize proximal causal inference framework for learning optimal dynamic treatment regimes when the unconfoundedness assumption fails. Our contributions are four-fold: (i) we propose three nonparametric identification methods for optimal dynamic treatment regimes; (ii) we establish the semiparametric efficiency bound for the value function of a given regime; (iii) we propose a (K+1)-robust method for learning optimal dynamic treatment regimes, where K is the number of stages; (iv) as a by-product for marginal structural models, we establish identification and estimation of counterfactual means under a static regime. Numerical experiments validate the efficiency and multiple robustness of our proposed methods.

Neural activity forecasting is central to understanding neural systems and enabling closed-loop control. While deep learning has recently advanced the state-of-the-art in the time series forecasting literature, its application to neural activity forecasting remains limited. To bridge this gap, we systematically evaluated eight probabilistic deep learning models, including two foundation models, that have demonstrated strong performance on general forecasting benchmarks. We compared them against four classical statistical models and two baseline methods on spontaneous neural activity recorded from mouse cortex via widefield imaging. Across prediction horizons, several deep learning models consistently outperformed classical approaches, with the best model producing informative forecasts up to 1.5 seconds into the future. Our findings point toward future control applications and open new avenues for probing the intrinsic temporal structure of neural activity.