Multi-Agent Coordination

Decentralized air traffic management systems offer a scalable alternative to centralized control, but often assume high levels of cooperation. In practice, such assumptions frequently break down since airspace sectors operate independently and prioritize local objectives. We address the problem of sector overload in decentralized air traffic management by proposing a regulated decentralized protocol that models self-interested behaviors based on best response dynamics. Each sector adjusts the departure times of flights under its control to reduce its own congestion, without requiring centralized joint optimization. A tunable cooperativeness factor models the degree to which each sector accounts for overload in other sectors, while a minimal admissibility rule prevents local updates from creating new overloads. We prove that the proposed protocol satisfies a potential game structure, ensuring that best response dynamics converge to a pure Nash equilibrium under this restriction. In addition, we identify a sufficient condition under which an overload-free solution corresponds to a global minimizer of the potential function. Numerical experiments using 24 hours of European flight data demonstrate that the proposed algorithm substantially reduces overload even with only minimal cooperation between sectors, while maintaining scalability and achieving solution quality comparable to the centralized benchmark.

Ad hoc teamwork (AHT) requires agents to collaborate with previously unseen teammates, which is crucial for many real-world applications. The core challenge of AHT is to develop an ego agent that can predict and adapt to unknown teammates on the fly. Conventional RL-based approaches optimize a single expected return, which often causes policies to collapse into a single dominant behavior, thus failing to capture the multimodal cooperation patterns inherent in AHT. In this work, we introduce PADiff, a diffusion-based approach that captures agent's multimodal behaviors, unlocking its diverse cooperation modes with teammates. However, standard diffusion models lack the ability to predict and adapt in highly non-stationary AHT scenarios. To address this limitation, we propose a novel diffusion-based policy that integrates critical predictive information about teammates into the denoising process. Extensive experiments across three cooperation environments demonstrate that PADiff outperforms existing AHT methods significantly.

Public resource allocation involves distributing resources, including urban infrastructure, energy, and transportation, which are typically limited in capacity, to meet social demands. In real-world scenarios, resources are typically limited in capacity, which makes coordination among multiple resources essential. However, existing methods often optimize resource movements in an isolated manner and do not explicitly account for capacity-aware collaboration under spatio-temporal dynamics. To address this limitation, we introduce the Collaborative Public Resource Allocation (CPRA) problem, and propose a Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL) framework to solve it. Our contributions are twofold: 1) We formulate CPRA as a potential game and construct the potential function based on the objective function of CPRA, laying a theoretical foundation for approximating the Nash equilibrium of this NP-hard problem; and 2) Our GSTRL framework effectively captures the spatio-temporal dynamics of the overall system. We evaluate GSTRL on two real-world datasets, where experiments show its superior performance. Our source codes are available at https://github.com/thunderlrr/GSTRL.

Efficient resource allocation in multi-agent systems requires autonomous agents to coordinate their decisions while balancing system-wide objectives with individual costs. This becomes increasingly challenging over long time horizons, where decisions that improve the current allocation may compromise future resource allocation, while decentralized agents have limited observations of the overall system. Multi-agent reinforcement learning (MARL) can learn such long-term dependencies via local observations, but directly applying it to large-scale coordination leads to rapidly growing decision spaces and inefficient training. To this end, we propose Hierarchical Reinforcement and Collective Learning (HRCL), a hierarchical framework that uses MARL to guide, rather than replace, decentralized multi-agent coordination. At the high level, MARL learns strategies that restrict the alternatives considered during coordination and guide agents in balancing system-wide and individual objectives. At the low level, agents perform efficient decentralized coordination under this strategic guidance. This separation reduces the learning space and allows short-term coordination trade-offs to be evaluated according to their long-term effects. Experiments on a synthetic benchmark show that HRCL converges substantially faster than standalone MARL and reduces system-wide and individual costs by 35.53% and 27.05%, respectively. Evaluations on energy self-management and drone swarm sensing further show improved resource allocation, power-peak regulation, and sensing efficiency. These results show that learning strategic guidance for an existing coordination process can retain scalable decentralized coordination without letting short-term decisions compromise future resource allocation.

As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such behaviors can be learned from expert demonstrations via imitation learning (IL), but when expert demonstrations are multi-modal, standard IL approaches usually average across modes or collapse to a single mode, preventing effective coordination. Being inspired by diffusion models' ability to capture complex multi-modal trajectory distributions in single-agent settings, we develop a diffusion-based framework for coordinated multi-modal behavior in multi-agent systems. However, existing multi-agent diffusion approaches typically require a centralized planner or explicit communication among agents. This assumption can fail in real-world scenarios where robots must operate independently or with agents like humans that they cannot directly communicate with. Therefore, we propose MIMIC-D, a joint training with decentralized execution paradigm for multi-modal multi-agent IL via diffusion. We jointly train all agents' policies with only local information to achieve implicit coordination. In simulation and hardware experiments, our method exhibits robust multi-modal coordination behavior in various tasks and environments, improving upon state-of-the-art baselines.

For groups of autonomous agents to achieve a particular goal, they must engage in coordination and long-horizon reasoning. Rather than relying on complex reward functions and explicit cooperation mechanisms, we ask what minimal ingredients are required for effective coordination and exploration to emerge in multi-agent settings. We investigate this question through self-supervised goal-reaching, where agents aim to maximize the likelihood of visiting a goal state rather than maximizing a reward. Despite a sparse feedback signal, we present empirical results that show self-supervised goal-reaching techniques enable agents to learn from such feedback. On MARL benchmarks, self-supervised goal-reaching outperforms alternative approaches that have access to the same sparse reward signal. Furthermore, we empirically demonstrate that multi-agent self-supervised goal-reaching approaches can be more robust than single-agent strategies. While there is no explicit exploration mechanism, this approach explores nontrivial intermediate coordination strategies in sparse settings where alternative approaches fail to achieve a single success.

Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goals, with applications in robot-assisted logistics and social navigation. Recent decentralized learned solvers have shown promise for large-scale MAPF, particularly when leveraging foundation models and large datasets. However, most existing methods rely on reactive policies, often resulting in congestion, deadlocks, and degraded generalization in high agent-density environments. To address these limitations, we propose MAPF-World, an autoregressive action world model for MAPF that unifies short-horizon local future prediction and action generation, enabling decision-making beyond immediate local observations. MAPF-World models short-horizon local dynamics by predicting the next local observation and neighboring agents' action intentions, capturing both spatial structures and temporal interaction patterns. We further introduce a spatio-agent positional encoding that integrates spatial awareness with agent-level semantics in Transformer-based architectures, facilitating more coordinated multi-agent behaviors. In addition, we augment existing MAPF benchmarks by introducing an automated map generator grounded in real-world urban layouts, aiming to narrow the gap between synthetic simulation and practical deployment scenarios. Extensive experiments across diverse map types and interaction settings demonstrate that MAPF-World achieves strong performance compared with existing learned solvers. Notably, it exhibits robust zero-shot generalization and maintains a high success rate even as agent density increases.

Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, the combination of these approaches has not been fully explored. To fill this void, we propose a novel and effective methodology for learning multi-agent hierarchies of message-passing policies. We adopt the feudal HRL framework and rely on a hierarchical graph structure for planning and coordination among agents. Agents at lower levels in the hierarchy receive goals from the upper levels and exchange messages with neighboring agents at the same level. To learn hierarchical multi-agent policies, we design a novel reward-assignment method based on training the lower-level policies to maximize the advantage function associated with the upper levels. Results on relevant benchmarks show that our method performs favorably compared to the state of the art.

Large Language Models (LLMs) exhibit a notable performance ceiling on complex, multi-faceted tasks. As practitioners increasingly rely on heavy context engineering -- curating intricate instructions, tool schemas, and multi-turn histories -- the processing demands often exceed the LLM's effective attention budget, leading to context rot. Drawing an analogy to Cognitive Load Theory (CLT) in cognitive science, we propose that this bottleneck is functionally analogous to the bounded working memory of the human mind. Rather than relying on heuristic prompt engineering, we use CLT as a principled design lens for LLM system design. To operationalize this insight, we introduce CoThinker, an instantiation of a CLT-driven multi-agent framework. CoThinker operationalizes CLT principles by distributing intrinsic cognitive load through agent specialization and managing transactional load via structured communication and a collective working memory. We empirically evaluate CoThinker on complex problem-solving tasks and fabricated high cognitive load scenarios. Our results are consistent with a CLT-informed account of multi-agent coordination: gains concentrate on reasoning-heavy tasks where cognitive load is high, while coordination overhead dominates on low-intrinsic-load tasks such as instruction-following -- a boundary predicted by the cognitive-load-profile view. Our analysis reveals characteristic interaction patterns that cast insights from collective cognition and load management into a principled approach to agent system design.

By aggregating distributed energy resources (DERs) into a single dispatchable resource, virtual power plants (VPPs) enable the grid to use the flexibility of numerous small-scale DERs. Delivering an aggregate VPP commitment requires multi-agent coordination, where agents manage local DER models and operating constraints while jointly meeting a power commitment within limited communication rounds. Classical distributed optimization is computationally intensive, requiring iterative local optimization and repeated communication to reach consensus. Learning-based methods can accelerate coordination but often lack guarantees of local feasibility and accurate commitment tracking. This paper proposes LOOP-MAC (Learning to Optimize the Optimization Process for Multi-Agent Coordination), a fully decentralized learning-based framework that ensures local feasibility by construction while efficiently reducing the aggregate commitment gap. LOOP-MAC employs a two-stage decision process. Learned coordination uses neural optimizers equipped with a gauge layer to produce locally feasible schedules through a few rounds of message exchange. Local adjustment then rebalances each schedule toward feasible flexibility extremes using a commitment-gap estimate inferred from messages already received. The adjusted schedule remains locally feasible as a convex combination of feasible schedules, and the adjustment requires no additional communication round. On a 100-agent VPP, five communication rounds followed by local adjustment reduce the mean commitment gap from 5.1% to 0.75% of the agents' aggregate absolute power and the optimality gap from 3.93% to 3.07% relative to learned coordination alone. Per-agent online computation takes approximately 1.1 ms, including the adjustment.