Centralized training with decentralized execution (CTDE) has achieved great success in cooperative multi-agent reinforcement learning (MARL) in practical applications. However, CTDE-based methods typically suffer from poor zero-shot generalization ability with dynamic team composition and varying partial observability. To tackle these issues, we propose a spontaneously grouping mechanism, termed Self-Organized Group (SOG), which is featured with conductor election (CE) and message summary (MS). In CE, a certain number of conductors are elected every $T$ time-steps to temporally construct groups, each with conductor-follower consensus where the followers are constrained to only communicate with their conductor. In MS, each conductor summarize and distribute the received messages to all affiliate group members to hold a unified scheduling. SOG provides zero-shot generalization ability to the dynamic number of agents and the varying partial observability.

The application of machine learning (ML) methods, a subfield of artificial intelligence (AI), to the solution of electromagnetic boundary value problems (BVPs) is currently a highly active area of research. Deep neural networks such as neural operators (Kovachki et al. 2023) and physics-informed neural networks, in which information about the BVP (and possibly measurement data) is integrated into the loss function of the network, often aim to replace traditional numerical methods such as the finite element (FE) method, compare, for example, with (Guo et al. 2025; Rezende and Schuhmann 2025). This work addresses an orthogonal problem: How can AI methods be used to reduce the time required to set up electromagnetic simulation models, rather than solving the numerical models themselves? The focus is thus on the assisted generation of simulation models, whereby the numerical scheme itself remains unaffected. A conceptually related direction has recently emerged in the computational fluid dynamics (CFD) community.

Graphical representation of the DNN based multi-fidelity surrogate model. In the experiments, we used three synthetic benchmark tasks to evaluate our method. The global maximum is -0.3979 at ( π, 12 .275) The materials are parameterized by three properties, Y oung's modulus (in To compute the frequency, we discretize the plate with quadratic tetrahedral elements (see Figure 1). The plate discretized with quadratic tetrahedral elements (the maximum mesh edge length is 1 .

In cooperative Multi-Agent Reinforcement Learning (MARL), efficient exploration is crucial for optimizing the performance of joint policy. However, existing methods often update joint policies via independent agent exploration, without coordination among agents, which inherently constrains the expressive capacity and exploration of joint policies. To address this issue, we propose a conductor-based joint policy framework that directly enhances the expressive capacity of joint policies and coordinates exploration. In addition, we develop a Hierarchical Conductor-based Policy Optimization (HCPO) algorithm that instructs policy updates for the conductor and agents in a direction aligned with performance improvement. A rigorous theoretical guarantee further establishes the monotonicity of the joint policy optimization process. By deploying local conductors, HCPO retains centralized training benefits while eliminating inter-agent communication during execution. Finally, we evaluate HCPO on three challenging benchmarks: Star-CraftII Multi-agent Challenge, Multi-agent MuJoCo, and Multi-agent Particle Environment. The results indicate that HCPO outperforms competitive MARL baselines regarding cooperative efficiency and stability.

It's critical to deal with the dynamic team composition in real-world multi-agent scenarios. MHA can easily achieve agents' partial observability with entity-wise expression. We commit our code in https://github.com/thu-rllab/SOG . 1 D Derivation of Message Summarizer For StarCraft Micromanagement Tasks, it takes about 20 hours to run one experiment. We summarize some hyper-parameters in Table. The radius of the home and the resource location & agent is 0.1 and 0.05, respectively.

However, the number of involved agents tends to vary in real-world multi-agent scenarios.

Drones can inspect overhead power lines while they remain energized, significantly simplifying the inspection process. However, localizing a drone relative to all conductors using an onboard LiDAR sensor presents several challenges: (1) conductors provide minimal surface for LiDAR beams limiting the number of conductor points in a scan, (2) not all conductors are consistently detected, and (3) distinguishing LiDAR points corresponding to conductors from other objects, such as trees and pylons, is difficult. This paper proposes an estimation approach that minimizes the error between LiDAR measurements and a single geometric model representing the entire conductor array, rather than tracking individual conductors separately. Experimental results, using data from a power line drone inspection, demonstrate that this method achieves accurate tracking, with a solver converging under 50 ms per frame, even in the presence of partial observations, noise, and outliers. A sensitivity analysis shows that the estimation approach can tolerate up to twice as many outlier points as valid conductors measurements.