Collaborative perception aims to extend sensing coverage and improve perception accuracy by sharing information among multiple agents. However, due to differences in viewpoints and spatial positions, agents often acquire heterogeneous observations. Existing intermediate fusion methods primarily focus on aligning similar features, often overlooking the perceptual diversity among agents. To address this limitation, we propose CoBEVMoE, a novel collaborative perception framework that operates in the Bird's Eye View (BEV) space and incorporates a Dynamic Mixture-of-Experts (DMoE) architecture. In DMoE, each expert is dynamically generated based on the input features of a specific agent, enabling it to extract distinctive and reliable cues while attending to shared semantics. This design allows the fusion process to explicitly model both feature similarity and heterogeneity across agents. Furthermore, we introduce a Dynamic Expert Metric Loss (DEML) to enhance inter-expert diversity and improve the discriminability of the fused representation. Extensive experiments on the OPV2V and DAIR-V2X-C datasets demonstrate that CoBEVMoE achieves state-of-the-art performance. Specifically, it improves the IoU for Camera-based BEV segmentation by +1.5% on OPV2V and the AP@50 for LiDAR-based 3D object detection by +3.0% on DAIR-V2X-C, verifying the effectiveness of expert-based heterogeneous feature modeling in multi-agent collaborative perception. The source code will be made publicly available at https://github.com/godk0509/CoBEVMoE.

Accurate trajectory prediction and motion planning are crucial for autonomous driving systems to navigate safely in complex, interactive environments characterized by multimodal uncertainties. However, current generation-then-evaluation frameworks typically construct multiple plausible trajectory hypotheses but ultimately adopt a single most likely outcome, leading to overconfident decisions and a lack of fallback strategies that are vital for safety in rare but critical scenarios. Moreover, the usual decoupling of prediction and planning modules could result in socially inconsistent or unrealistic joint trajectories, especially in highly interactive traffic. To address these challenges, we propose a contingency-aware diffusion planner (CoPlanner), a unified framework that jointly models multi-agent interactive trajectory generation and contingency-aware motion planning. Specifically, the pivot-conditioned diffusion mechanism anchors trajectory sampling on a validated, shared short-term segment to preserve temporal consistency, while stochastically generating diverse long-horizon branches that capture multimodal motion evolutions. In parallel, we design a contingency-aware multi-scenario scoring strategy that evaluates candidate ego trajectories across multiple plausible long-horizon evolution scenarios, balancing safety, progress, and comfort. This integrated design preserves feasible fallback options and enhances robustness under uncertainty, leading to more realistic interaction-aware planning. Extensive closed-loop experiments on the nuPlan benchmark demonstrate that CoPlanner consistently surpasses state-of-the-art methods on both Val14 and Test14 datasets, achieving significant improvements in safety and comfort under both reactive and non-reactive settings. Code and model will be made publicly available upon acceptance.

The advancement of foundation models fosters new initiatives for policy learning in achieving safe and efficient autonomous driving. However, a critical bottleneck lies in the manual engineering of reward functions and training curricula for complex and dynamic driving tasks, which is a labor-intensive and time-consuming process. To address this problem, we propose OGR (Orchestrate, Generate, Reflect), a novel automated driving policy learning framework that leverages vision-language model (VLM)-based multi-agent collaboration. Our framework capitalizes on advanced reasoning and multimodal understanding capabilities of VLMs to construct a hierarchical agent system. Specifically, a centralized orchestrator plans high-level training objectives, while a generation module employs a two-step analyze-then-generate process for efficient generation of reward-curriculum pairs. A reflection module then facilitates iterative optimization based on the online evaluation. Furthermore, a dedicated memory module endows the VLM agents with the capabilities of long-term memory. To enhance robustness and diversity of the generation process, we introduce a parallel generation scheme and a human-in-the-loop technique for augmentation of the reward observation space. Through efficient multi-agent cooperation and leveraging rich multimodal information, OGR enables the online evolution of reinforcement learning policies to acquire interaction-aware driving skills. Extensive experiments in the CARLA simulator demonstrate the superior performance, robust generalizability across distinct urban scenarios, and strong compatibility with various RL algorithms. Further real-world experiments highlight the practical viability and effectiveness of our framework. The source code will be available upon acceptance of the paper.

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with limited capacity. Prior works attempt to distill information from large teacher models using behavior cloning or KL divergence. These methods often focus on mimicking current behavior and overlook distilling reward modeling. To address this issue, we propose \textit{Teacher Value-based Knowledge Distillation} (TVKD), which introduces an auxiliary reward from the value function of the teacher model to provide a soft guide. This auxiliary reward is formulated to satisfy potential-based reward shaping, ensuring that the global reward structure and optimal policy of DPO are preserved. TVKD can be integrated into the standard DPO training framework and does not require additional rollouts. Our experimental results show that TVKD consistently improves performance across various benchmarks and model sizes.

In audio-visual navigation (A VN) tasks, an embodied agent must autonomously localize a sound source in unknown and complex 3D environments based on audio-visual signals. Existing methods often rely on static modality fusion strategies and neglect the spatial cues embedded in stereo audio, leading to performance degradation in cluttered or occluded scenes. To address these issues, we propose an end-to-end reinforcement learning-based AVN framework with two key innovations: (1) a Stereo-Aware Attention Module (SAM), which learns and exploits the spatial disparity between left and right audio channels to enhance directional sound perception; and (2) an Audio-Guided Dynamic Fusion Module (AGDF), which dynamically adjusts the fusion ratio between visual and auditory features based on audio cues, thereby improving robustness to environmental changes. Extensive experiments are conducted on two realistic 3D scene datasets, Replica and Matterport3D, demonstrating that our method significantly outperforms existing approaches in terms of navigation success rate and path efficiency. Notably, our model achieves over 40% improvement under audio-only conditions compared to the best-performing baselines.

Order book imbalance (OBI) - buy orders minus sell orders near the best quote - measures supply-demand imbalance that can move prices. OBI is positively correlated with returns, and some investors try to use it to improve performance. Large orders placed at once can reveal intent, invite front-running, raise volatility, and cause losses. Execution algorithms therefore split parent orders into smaller lots to limit price distortion. In principle, using OBI inside such algorithms could improve execution, but prior evidence is scarce because isolating OBI's effect in real markets is nearly impossible amid many external factors. Multi-agent simulation offers a way to study this. In an artificial market, individual actors are agents whose rules and interactions form the model. This study builds an execution algorithm that accounts for OBI, tests it across several market patterns in artificial markets, and analyzes mechanisms, comparing it with a conventional (OBI-agnostic) algorithm. Results: (i) In stable markets, the OBI strategy's performance depends on the number of order slices; outcomes vary with how the parent order is partitioned. (ii) In markets with unstable prices, the OBI-based algorithm outperforms the conventional approach. (iii) Under spoofing manipulation, the OBI strategy is not significantly worse than the conventional algorithm, indicating limited vulnerability to spoofing. Overall, OBI provides a useful signal for execution. Incorporating OBI can add value - especially in volatile conditions - while remaining reasonably robust to spoofing; in calm markets, benefits are sensitive to slicing design.

Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized environments where communication lacks transparency and agent behavior cannot be shaped through centralized incentives. We propose a blockchain-based framework that enables transparent agent registration, verifiable task allocation, and dynamic reputation tracking through smart contracts. The core of our design lies in two mechanisms: a matching score-based task allocation protocol that evaluates agents by reputation, capability match, and workload; and a behavior-shaping incentive mechanism that adjusts agent behavior via feedback on performance and reward. Our implementation integrates GPT-4 agents with Solidity contracts and demonstrates, through 50-round simulations, strong task success rates, stable utility distribution, and emergent agent specialization. The results underscore the potential for trustworthy, incentive-compatible multi-agent coordination in open environments.

LLM-based Interactive Drama introduces a novel dialogue scenario in which the player immerses into a character and engages in a dramatic story by interacting with LLM agents. Despite the fact that this emerging area holds significant promise, it remains largely underexplored due to the lack of a well-designed playground to develop a complete drama. This makes a significant barrier for researchers to replicate, extend, and study such systems. Hence, we present Open-Theatre, the first open-source toolkit for experiencing and customizing LLM-based interactive drama. It refines prior work with an efficient multi-agent architecture and a hierarchical retrieval-based memory system, designed to enhance narrative coherence and realistic long-term behavior in complex interactions. In addition, we provide a highly configurable pipeline, making it easy for researchers to develop and optimize new approaches.

Deep reinforcement learning has recently emerged as a promising feedback control strategy for complex dynamical systems governed by partial differential equations (PDEs). When dealing with distributed, high-dimensional problems in state and control variables, multi-agent reinforcement learning (MARL) has been proposed as a scalable approach for breaking the curse of dimensionality. In particular, through decentralized training and execution, multiple agents cooperate to steer the system towards a target configuration, relying solely on local state and reward information. However, the principle of locality may become a limiting factor whenever a collective, nonlocal behavior of the agents is crucial to maximize the reward function, as typically happens in PDE-constrained optimal control problems. In this work, we propose HypeMARL: a decentralized MARL algorithm tailored to the control of high-dimensional, parametric, and distributed systems. HypeMARL employs hypernetworks to effectively parametrize the agents' policies and value functions with respect to the system parameters and the agents' relative positions, encoded by sinusoidal positional encoding. Through the application on challenging control problems, such as density and flow control, we show that HypeMARL (i) can effectively control systems through a collective behavior of the agents, outperforming state-of-the-art decentralized MARL, (ii) can efficiently deal with parametric dependencies, (iii) requires minimal hyperparameter tuning and (iv) can reduce the amount of expensive environment interactions by a factor of ~10 thanks to its model-based extension, MB-HypeMARL, which relies on computationally efficient deep learning-based surrogate models approximating the dynamics locally, with minimal deterioration of the policy performance.

Distributed quantum machine learning faces significant challenges due to heterogeneous client data and variations in local model structures, which hinder global model aggregation. To address these challenges, we propose a knowledge distillation framework for variational quantum convolutional neural networks on heterogeneous data. The framework features a quantum gate number estimation mechanism based on client data, which guides the construction of resource-adaptive VQCNN circuits. Particle swarm optimization is employed to efficiently generate personalized quantum models tailored to local data characteristics. During aggregation, a knowledge distillation strategy integrating both soft-label and hard-label supervision consolidates knowledge from heterogeneous clients using a public dataset, forming a global model while avoiding parameter exposure and privacy leakage. Theoretical analysis shows that proposed framework benefits from quantum high-dimensional representation, offering advantages over classical approaches, and minimizes communication by exchanging only model indices and test outputs. Extensive simulations on the PennyLane platform validate the effectiveness of the gate number estimation and distillation-based aggregation. Experimental results demonstrate that the aggregated global model achieves accuracy close to fully supervised centralized training. These results shown that proposed methods can effectively handle heterogeneity, reduce resource consumption, and maintain performance, highlighting its potential for scalable and privacy-preserving distributed quantum learning.