Modern healthcare has achieved remarkable success in moments of crisis -- with technology-rich environments like the Intensive Care Unit (ICU) offering extraordinary precision, real-time monitoring, and expert-led interventions. In the ICU, a team of professionals continuously tracks a wide array of biomarkers, interprets their trends, and delivers timely care with orchestration and rigor. Y et, this reactive strength has come at the expense of a deeper, more continuous engagement with health as it unfolds in everyday life. This limitation was first articulated in the early calls for precision and P4 medicine, which envisioned predictive, personalized, preventive, and participatory models of care that would complement traditional clinical practice [1, 2, 3]. This imbalance is starkly captured in what we call the "8759 vs. 1" paradox: an individual spends 8759 hours each year outside the clinical setting, making decisions that shape their health -- while barely an hour is spent in direct consultation with care providers. During those other hours, health is continuously influenced by behavior, environment, emotion, and social context. Y et, our existing computing systems remain fixated on the one hour, neglecting the remaining 8759. 1

Abstract--The reliability of Simultaneous Localization and Mapping (SLAM) is severely constrained in environments where visual inputs suffer from noise and low illumination. Although recent 3D Gaussian Splatting (3DGS) based SLAM frameworks achieve high-fidelity mapping under clean conditions, they remain vulnerable to compounded degradations that degrade mapping and tracking performance. A key observation underlying our work is that the original 3DGS rendering pipeline inherently behaves as an implicit low-pass filter, attenuating high-frequency noise but also risking over-smoothing. Building on this insight, we propose RoGER-SLAM, a robust 3DGS SLAM system tailored for noise and low-light resilience. The framework integrates three innovations: a Structure-Preserving Robust Fusion (SP-RoFusion) mechanism that couples rendered appearance, depth, and edge cues; an adaptive tracking objective with residual balancing regularization; and a Contrastive Language-Image Pretraining (CLIP)-based enhancement module, selectively activated under compounded degradations to restore semantic and structural fidelity. Comprehensive experiments on Replica, TUM, and real-world sequences show that RoGER-SLAM consistently improves trajectory accuracy and reconstruction quality compared with other 3DGS-SLAM systems, especially under adverse imaging conditions. IMUL T ANEOUS Localization and Mapping (SLAM) persists as a foundational capability for autonomous systems operating in unstructured environments, with mission-critical applications in robotics, augmented reality, and autonomous driving. With the advancement of SLAM research, the focus has gradually shifted beyond localization accuracy toward achieving photorealistic and structurally consistent map reconstruction. In this context, neural rendering techniques such as Neural Radiance Fields (NeRF) [1] have demonstrated impressive photorealistic reconstruction capabilities by representing scenes as continuous volumetric fields. However, NeRF-based SLAM approaches [2], [3], [4], [5], [6], [7] often suffer from high computational cost, slow convergence and weak structural regularization, which limit their applicability in real-time and degraded scenarios. This work was supported by the National Natural Science Foundation of China under Grant No. 62433014 and No.62133011.

The coordination of multiple autonomous agents in high-speed, competitive environments represents a significant engineering challenge. This paper presents CRUISE (Curriculum-Based Iterative Self-Play for Scalable Multi-Drone Racing), a reinforcement learning framework designed to solve this challenge in the demanding domain of multi-drone racing. CRUISE overcomes key scalability limitations by synergistically combining a progressive difficulty curriculum with an efficient self-play mechanism to foster robust competitive behaviors. Validated in high-fidelity simulation with realistic quadrotor dynamics, the resulting policies significantly outperform both a standard reinforcement learning baseline and a state-of-the-art game-theoretic planner. CRUISE achieves nearly double the planner's mean racing speed, maintains high success rates, and demonstrates robust scalability as agent density increases. Ablation studies confirm that the curriculum structure is the critical component for this performance leap. By providing a scalable and effective training methodology, CRUISE advances the development of autonomous systems for dynamic, competitive tasks and serves as a blueprint for future real-world deployment.

As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on tasks that require deep knowledge and skills of multiple domains. Unfortunately, even the best human experts are knowledgeable only in a single narrow area, and will not be able to evaluate the correctness of advanced AI systems on such superhuman tasks. However, based on their narrow expertise, humans may provide a weak signal, i.e., a complementary label indicating an option that is incorrect. For example, a cardiologist could state that "this is not related to cardiology,'' even if they cannot identify the true disease. Based on this weak signal, we propose a scalable oversight framework that enables us to evaluate frontier AI systems without the need to prepare the ground truth. We derive an unbiased estimator of top-1 accuracy from complementary labels and quantify how many complementary labels are needed to match the variance of ordinary labels. We further introduce two estimators to combine scarce ordinary labels with abundant complementary labels. We provide finite-sample deviation guarantees for both complementary-only and the mixed estimators. Empirically, we show that we can evaluate the output of large language models without the ground truth, if we have complementary labels. We further show that we can train an AI system with such weak signals: we show how we can design an agentic AI system automatically that can perform better with this partitioned human supervision. Our code is available at https://github.com/R-Yin-217/Scalable-Oversight-via-Human-Partitioned-Supervision.

To combat the prohibitive communication costs of ``free-for-all" multi-agent systems (MAS), we introduce \textbf{Agent-GSPO}, a framework that directly optimizes for token economy using sequence-level reinforcement learning. Agent-GSPO leverages the stable and memory-efficient Group Sequence Policy Optimization (GSPO) algorithm to train agents on a communication-aware reward that explicitly penalizes verbosity. Across seven reasoning benchmarks, Agent-GSPO not only achieves new state-of-the-art performance but does so with a fraction of the token consumption of existing methods. By fostering emergent strategies like ``strategic silence," our approach provides a practical blueprint for developing scalable and economically viable multi-agent systems.

Recent advancements in multi-agent systems have demonstrated significant potential for enhancing creative task performance, such as long video generation. This study introduces three innovations to improve multi-agent collaboration. First, we propose OmniAgent, a hierarchical, graph-based multi-agent framework for long video generation that leverages a film-production-inspired architecture to enable modular specialization and scalable inter-agent collaboration. Second, inspired by context engineering, we propose hypergraph nodes that enable temporary group discussions among agents lacking sufficient context, reducing individual memory requirements while ensuring adequate contextual information. Third, we transition from directed acyclic graphs (DAGs) to directed cyclic graphs with limited retries, allowing agents to reflect and refine outputs iteratively, thereby improving earlier stages through feedback from subsequent nodes. These contributions lay the groundwork for developing more robust multi-agent systems in creative tasks.

Multi-agent systems of large language models (LLMs) are rapidly expanding across domains, introducing dynamics not captured by single-agent evaluations. Yet, existing work has mostly contrasted the behavior of a single agent with that of a collective of fixed size, leaving open a central question: how does group size shape dynamics? Here, we move beyond this dichotomy and systematically explore outcomes across the full range of group sizes. We focus on multi-agent misalignment, building on recent evidence that interacting LLMs playing a simple coordination game can generate collective biases absent in individual models. First, we show that collective bias is a deeper phenomenon than previously assessed: interaction can amplify individual biases, introduce new ones, or override model-level preferences. Second, we demonstrate that group size affects the dynamics in a non-linear way, revealing model-dependent dynamical regimes. Finally, we develop a mean-field analytical approach and show that, above a critical population size, simulations converge to deterministic predictions that expose the basins of attraction of competing equilibria. These findings establish group size as a key driver of multi-agent dynamics and highlight the need to consider population-level effects when deploying LLM-based systems at scale.

Controlling high-dimensional stochastic systems, critical in robotics, autonomous vehicles, and hyperchaotic systems, faces the curse of dimensionality, lacks temporal abstraction, and often fails to ensure stochastic stability. To overcome these limitations, this study introduces the Multi-Timescale Lyapunov-Constrained Hierarchical Reinforcement Learning (MTLHRL) framework. MTLHRL integrates a hierarchical policy within a semi-Markov Decision Process (SMDP), featuring a high-level policy for strategic planning and a low-level policy for reactive control, which effectively manages complex, multi-timescale decision-making and reduces dimensionality overhead. Stability is rigorously enforced using a neural Lyapunov function optimized via Lagrangian relaxation and multi-timescale actor-critic updates, ensuring mean-square boundedness or asymptotic stability in the face of stochastic dynamics. The framework promotes efficient and reliable learning through trust-region constraints and decoupled optimization. Extensive simulations on an 8D hyperchaotic system and a 5-DOF robotic manipulator demonstrate MTLHRL's empirical superiority. It significantly outperforms baseline methods in both stability and performance, recording the lowest error indices (e.g., Integral Absolute Error (IAE): 3.912 in hyperchaotic control and IAE: 1.623 in robotics), achieving faster convergence, and exhibiting superior disturbance rejection. MTLHRL offers a theoretically grounded and practically viable solution for robust control of complex stochastic systems.

The integration of self-driving cars and service robots is becoming increasingly prevalent across a wide array of fields, playing a crucial and expanding role in both industrial applications and everyday life. In parallel, the rapid advancements in Large Language Models (LLMs) have garnered substantial attention and interest within the research community. This paper introduces a novel vehicle-robot system that leverages the strengths of both autonomous vehicles and service robots. In our proposed system, two autonomous ego-vehicles transports service robots to locations within an office park, where they perform a series of tasks. The study explores the feasibility and potential benefits of incorporating LLMs into this system, with the aim of enhancing operational efficiency and maximizing the potential of the cooperative mechanisms between the vehicles and the robots. This paper proposes a novel inference mechanism which is called CGOT toward this type of system where an agent can carry another agent. Experimental results are presented to validate the performance of the proposed method.

Cooperative systems often remain in persistently suboptimal yet stable states. This paper explains such "rational stagnation" as an equilibrium sustained by a rational adversary whose utility follows the principle of potential loss, $u_{D} = U_{ideal} - U_{actual}$. Starting from the Prisoner's Dilemma, we show that the transformation $u_{i}' = a\,u_{i} + b\,u_{j}$ and the ratio of mutual recognition $w = b/a$ generate a fragile cooperation band $[w_{\min},\,w_{\max}]$ where both (C,C) and (D,D) are equilibria. Extending to a dynamic model with stochastic cooperative payoffs $R_{t}$ and intervention costs $(C_{c},\,C_{m})$, a Bellman-style analysis yields three strategic regimes: immediate destruction, rational stagnation, and intervention abandonment. The appendix further generalizes the utility to a reference-dependent nonlinear form and proves its stability under reference shifts, ensuring robustness of the framework. Applications to social-media algorithms and political trust illustrate how adversarial rationality can deliberately preserve fragility.