Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the synchronous updates of agent policies. This non stationarity results in unstable training and poor policy con vergence, especially as the number of agents increases. In this paper, we propose RELED, a scalable MARL framework that integrates large language model (LLM)-driven expert demonstrations with autonomous agent exploration. RELED incorporates a Stationarity-Aware Expert Demonstration module, which leverages theoretical non-stationarity bounds to enhance the quality of LLM-generated expert trajectories, thus providing high reward and training-stable samples for each agent. Moreover, a Hybrid Expert-Agent Policy Optimization module adaptively balances each agent's learning from both expert-generated and agent-generated trajectories, accelerating policy convergence and improving generalization. Extensive experiments with real city networks based on OpenStreetMap demonstrate that RELED achieves superior performance compared to state-of-the-art MARL methods.
Cooperative Multi-Agent Reinforcement Learning (MARL) faces two major design bottlenecks: crafting dense reward functions and constructing curricula that avoid local optima in high-dimensional, non-stationary environments. Existing approaches rely on fixed heuristics or use Large Language Models (LLMs) directly in the control loop, which is costly and unsuitable for real-time systems. We propose MAESTRO (Multi-Agent Environment Shaping through Task and Reward Optimization), a framework that moves the LLM outside the execution loop and uses it as an offline training architect. MAESTRO introduces two generative components: (i) a semantic curriculum generator that creates diverse, performance-driven traffic scenarios, and (ii) an automated reward synthesizer that produces executable Python reward functions adapted to evolving curriculum difficulty. These components guide a standard MARL backbone (MADDPG) without increasing inference cost at deployment. We evaluate MAESTRO on large-scale traffic signal control (Hangzhou, 16 intersections) and conduct controlled ablations. Results show that combining LLM-generated curricula with LLM-generated reward shaping yields improved performance and stability. Across four seeds, the full system achieves +4.0% higher mean return (163.26 vs. 156.93) and 2.2% better risk-adjusted performance (Sharpe 1.53 vs. 0.70) over a strong curriculum baseline. These findings highlight LLMs as effective high-level designers for cooperative MARL training.
Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning(MARL) systems. However, the inherent communication latency in practical systems induces both action decision delays and outdated information sharing, impeding MARL performance gains, particularly in time-critical applications like autonomous driving. In this work, we propose a Value-of-Information aware Low-latency Communication(VIL2C) scheme that proactively adjusts the latency distribution to mitigate its effects in MARL systems. Specifically, we define a Value of Information (VOI) metric to quantify the importance of delayed message transmission based on each delayed message's importance. Moreover, we propose a progressive message reception mechanism to adaptively adjust the reception duration based on received messages. We derive the optimized VoI aware resource allocation and theoretically prove the performance advantage of the proposed VIL2C scheme. Extensive experiments demonstrate that VIL2C outperforms existing approaches under various communication conditions. These gains are attributed to the low-latency transmission of high-VoI messages via resource allocation and the elimination of unnecessary waiting periods via adaptive reception duration.
By leveraging tool-augmented Multimodal Large Language Models (MLLMs), multi-agent frameworks are driving progress in video understanding. However, most of them adopt static and non-learnable tool invocation mechanisms, which limit the discovery of diverse clues essential for robust perception and reasoning regarding temporally or spatially complex videos. To address this challenge, we propose a novel Multi-agent system for video understanding, namely VideoChat-M1. Instead of using a single or fixed policy, VideoChat-M1 adopts a distinct Collaborative Policy Planning (CPP) paradigm with multiple policy agents, which comprises three key processes. (1) Policy Generation: Each agent generates its unique tool invocation policy tailored to the user's query; (2) Policy Execution: Each agent sequentially invokes relevant tools to execute its policy and explore the video content; (3) Policy Communication: During the intermediate stages of policy execution, agents interact with one another to update their respective policies. Through this collaborative framework, all agents work in tandem, dynamically refining their preferred policies based on contextual insights from peers to effectively respond to the user's query. Moreover, we equip our CPP paradigm with a concise Multi-Agent Reinforcement Learning (MARL) method. Consequently, the team of policy agents can be jointly optimized to enhance VideoChat-M1's performance, guided by both the final answer reward and intermediate collaborative process feedback. Extensive experiments demonstrate that VideoChat-M1 achieves SOTA performance across eight benchmarks spanning four tasks. Notably, on LongVideoBench, our method outperforms the SOTA model Gemini 2.5 pro by 3.6% and GPT-4o by 15.6%.
In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., ``\textit{Tell}'') can assist in the cognitive development process by information dissemination, yet it is inevitably subject to real-world constraints such as noise, latency, and attacks. Therefore, building the understanding of teammates' decisions without communication remains challenging. To address this, we propose a novel non-communication MARL framework that realizes the construction of cognition through local observation-based modeling (i.e., \textit{``Think''}). Our framework enables agents to model teammates' \textbf{active inference} process. At first, the proposed method produces three teammate portraits: perception-belief-action. Specifically, we model the teammate's decision process as follows: 1) Perception: observing environments; 2) Belief: forming beliefs; 3) Action: making decisions. Then, we selectively integrate the belief portrait into the decision process based on the accuracy and relevance of the perception portrait. This enables the selection of cooperative teammates and facilitates effective collaboration. Extensive experiments on the SMAC, SMACv2, MPE, and GRF benchmarks demonstrate the superior performance of our method.
Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However, centralized-decentralized mismatch (CDM) arises when the suboptimal behavior of one agent degrades others' learning. Prior approaches mitigate CDM through value decomposition, but linear decompositions allow per-agent gradients at the cost of limited expressiveness, while nonlinear decompositions improve representation but require centralized gradients, reintroducing CDM. To overcome this trade-off, we propose the multi-agent cross-entropy method (MCEM), combined with monotonic nonlinear critic decomposition (NCD). MCEM updates policies by increasing the probability of high-value joint actions, thereby excluding suboptimal behaviors. For sample efficiency, we extend off-policy learning with a modified k-step return and Retrace. Analysis and experiments demonstrate that MCEM outperforms state-of-the-art methods across both continuous and discrete action benchmarks.
Spatial task allocation in systems such as multi-robot delivery or ride-sharing requires balancing efficiency with fair service across tasks. Greedy assignment policies that match each agent to its highest-preference or lowest-cost task can maximize efficiency but often create inequities: some tasks receive disproportionately favorable service (e.g., shorter delays or better matches), while others face long waits or poor allocations. We study fairness in heterogeneous multi-agent systems where tasks vary in preference alignment and urgency. Most existing approaches either assume centralized coordination or largely ignore fairness under partial observability. Distinct from this prior work, we establish a connection between the Eisenberg-Gale (EG) equilibrium convex program and decentralized, partially observable multi-agent learning. Building on this connection, we develop two equilibrium-informed algorithms that integrate fairness and efficiency: (i) a multi-agent reinforcement learning (MARL) framework, EG-MARL, whose training is guided by centralized fair assignment algorithms (EG and a preference-aware Hungarian method); and (ii) a stochastic online optimization mechanism that performs guided exploration and subset-based fair assignment as tasks are discovered. We evaluate our frameworks across a range of team sizes and assignment formulations against centralized EG, Hungarian, and Min-Max Distance baselines. Both algorithms preserve the fairness-efficiency balance of the Eisenberg-Gale equilibrium under partial observability. EG-MARL achieves near-centralized coordination and reduced travel distances, while the stochastic online mechanism enables real-time allocation with competitive fairness. Together, these results demonstrate that spatially aware EG formulations can effectively guide decentralized coordination in agents with heterogeneous capabilities.
Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement learn-ing (MARL) remains problematic. The primary difficulties stem from two fac-tors: (1) the exponential sparsity of joint action trajectories that lead to rewards as the exploration space expands, and (2) existing methods often fail to account for joint actions that can influence team states. To address these challenges, this paper introduces Mutual Intrinsic Reward (MIR), a simple yet effective enhancement strategy for MARL with extremely sparse rewards like episodic rewards. MIR incentivizes individual agents to explore actions that affect their teammates, and when combined with original strategies, effectively stimulates team exploration and improves algorithm performance. For comprehensive experimental valida-tion, we extend the representative single-agent MiniGrid environment to create MiniGrid-MA, a series of MARL environments with sparse rewards. Our evalu-ation compares the proposed method against state-of-the-art approaches in the MiniGrid-MA setting, with experimental results demonstrating superior perfor-mance.
Conflict resolution and consensus building represent critical challenges in multi-agent systems, negotiations, and collaborative decision-making processes. This paper introduces Dialogue Diplomats, a novel end-to-end multi-agent reinforcement learning (MARL) framework designed for automated conflict resolution and consensus building in complex, dynamic environments. The proposed system integrates advanced deep reinforcement learning architectures with dialogue-based negotiation protocols, enabling autonomous agents to engage in sophisticated conflict resolution through iterative communication and strategic adaptation. We present three primary contributions: first, a novel Hierarchical Consensus Network (HCN) architecture that combines attention mechanisms with graph neural networks to model inter-agent dependencies and conflict dynamics. second, a Progressive Negotiation Protocol (PNP) that structures multi-round dialogue interactions with adaptive concession strategies; and third, a Context-Aware Reward Shaping mechanism that balances individual agent objectives with collective consensus goals.
Multi-Agent Reinforcement Learning (MARL) has emerged as a powerfulparadigm for cooperative decision-making in connected autonomous vehicles(CAVs); however, existing approaches often fail to guarantee stability, optimality,and interpretability in systems characterized by nonlinear dynamics,partial observability, and complex inter-agent coupling. This study addressesthese foundational challenges by introducing MARL-CC, a unified MathematicalFramework for Multi-Agent Reinforcement Learning with Control Coordination.The proposed framework integrates differential geometric control, Bayesian inference,and Shapley-value-based credit assignment within a coherent optimizationarchitecture, ensuring bounded policy updates, decentralized belief estimation,and equitable reward distribution. Theoretical analyses establish convergence andstability guarantees under stochastic disturbances and communication delays.Empirical evaluations across simulation and real-world testbeds demonstrate upto a 40% improvement in convergence rate and enhanced cooperative efficiencyover leading baselines, including PPO, DDPG, and QMIX.These results signify a decisive advance in control-oriented reinforcement learning,bridging the gap between mathematical rigor and practical autonomy.The MARL-CC framework provides a scalable foundation for intelligent transportation,UAV coordination, and distributed robotics, paving the way toward interpretable, safe, and adaptive multi-agent systems. All codes and experimentalconfigurations are publicly available on GitHub to support reproducibilityand future research.
Next-generation networks utilize the Open Radio Access Network (O-RAN) architecture to enable dynamic resource management, facilitated by the RAN Intelligent Controller (RIC). While deep reinforcement learning (DRL) models show promise in optimizing network resources, they often struggle with robustness and generalizability in dynamic environments. This paper introduces a novel resource management approach that enhances the Soft Actor Critic (SAC) algorithm with Sharpness-Aware Minimization (SAM) in a distributed Multi-Agent RL (MARL) framework. Our method introduces an adaptive and selective SAM mechanism, where regularization is explicitly driven by temporal-difference (TD)-error variance, ensuring that only agents facing high environmental complexity are regularized. This targeted strategy reduces unnecessary overhead, improves training stability, and enhances generalization without sacrificing learning efficiency. We further incorporate a dynamic $ρ$ scheduling scheme to refine the exploration-exploitation trade-off across agents. Experimental results show our method significantly outperforms conventional DRL approaches, yielding up to a $22\%$ improvement in resource allocation efficiency and ensuring superior QoS satisfaction across diverse O-RAN slices.
Ramp merging is a critical and challenging task for autonomous vehicles (AVs), particularly in mixed traffic environments with human-driven vehicles (HVs). Existing approaches typically rely on either lane-changing or inter-vehicle gap creation strategies based solely on local or neighboring information, often leading to suboptimal performance in terms of safety and traffic efficiency. In this paper, we present a V2X (vehicle-to-everything communication)-assisted Multiagent Reinforcement Learning (MARL) framework for on-ramp merging that effectively coordinates the complex interplay between lane-changing and inter-vehicle gap adaptation strategies by utilizing zone-specific global information available from a roadside unit (RSU). The merging control problem is formulated as a Multiagent Partially Observable Markov Decision Process (MA-POMDP), where agents leverage both local and global observations through V2X communication. To support both discrete and continuous control decisions, we design a hybrid action space and adopt a parameterized deep Q-learning approach. Extensive simulations, integrating the SUMO traffic simulator and the MOSAIC V2X simulator, demonstrate that our framework significantly improves merging success rate, traffic efficiency, and road safety across diverse traffic scenarios.
Enforcing a fair workload allocation among multiple agents tasked to achieve an objective in learning enabled demand side healthcare worker settings is crucial for consistent and reliable performance at runtime. Existing multi-agent reinforcement learning (MARL) approaches steer fairness by shaping reward through post hoc orchestrations, leaving no certifiable self-enforceable fairness that is immutable by individual agents at runtime. Contextualized within a setting where each agent shares resources with others, we address this shortcoming with a learning enabled optimization scheme among self-interested decision makers whose individual actions affect those of other agents. This extends the problem to a generalized Nash equilibrium (GNE) game-theoretic framework where we steer group policy to a safe and locally efficient equilibrium, so that no agent can improve its utility function by unilaterally changing its decisions. Fair-GNE models MARL as a constrained generalized Nash equilibrium-seeking (GNE) game, prescribing an ideal equitable collective equilibrium within the problem's natural fabric. Our hypothesis is rigorously evaluated in our custom-designed high-fidelity resuscitation simulator. Across all our numerical experiments, Fair-GNE achieves significant improvement in workload balance over fixed-penalty baselines (0.89 vs.\ 0.33 JFI, $p < 0.01$) while maintaining 86\% task success, demonstrating statistically significant fairness gains through adaptive constraint enforcement. Our results communicate our formulations, evaluation metrics, and equilibrium-seeking innovations in large multi-agent learning-based healthcare systems with clarity and principled fairness enforcement.
Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in dynamic and uncertain environments. However, learning dynamic task decomposition from scratch generally requires a large number of training samples, especially exploring the large joint action space under partial observability. In this paper, we present the Conditional Diffusion Model for Dynamic Task Decomposition (C$\text{D}^\text{3}$T), a novel two-level hierarchical MARL framework designed to automatically infer subtask and coordination patterns. The high-level policy learns subtask representation to generate a subtask selection strategy based on subtask effects. To capture the effects of subtasks on the environment, C$\text{D}^\text{3}$T predicts the next observation and reward using a conditional diffusion model. At the low level, agents collaboratively learn and share specialized skills within their assigned subtasks. Moreover, the learned subtask representation is also used as additional semantic information in a multi-head attention mixing network to enhance value decomposition and provide an efficient reasoning bridge between individual and joint value functions. Experimental results on various benchmarks demonstrate that C$\text{D}^\text{3}$T achieves better performance than existing baselines.
Multi-agent reinforcement learning (MARL) has shown promise for large-scale network control, yet existing methods face two major limitations. First, they typically rely on assumptions leading to decay properties of local agent interactions, limiting their ability to capture long-range dependencies such as cascading power failures or epidemic outbreaks. Second, most approaches lack generalizability across network topologies, requiring retraining when applied to new graphs. We introduce STACCA (Shared Transformer Actor-Critic with Counterfactual Advantage), a unified transformer-based MARL framework that addresses both challenges. STACCA employs a centralized Graph Transformer Critic to model long-range dependencies and provide system-level feedback, while its shared Graph Transformer Actor learns a generalizable policy capable of adapting across diverse network structures. Further, to improve credit assignment during training, STACCA integrates a novel counterfactual advantage estimator that is compatible with state-value critic estimates. We evaluate STACCA on epidemic containment and rumor-spreading network control tasks, demonstrating improved performance, network generalization, and scalability. These results highlight the potential of transformer-based MARL architectures to achieve scalable and generalizable control in large-scale networked systems.
In post-disaster space-air-ground integrated networks (SAGINs), terrestrial infrastructure is often impaired, and unmanned aerial vehicles (UAVs) must rapidly restore connectivity for mission-critical ground terminals in cluttered non-line-of-sight (NLoS) urban environments. To enhance coverage, UAVs employ movable antennas (MAs), while reconfigurable intelligent surfaces (RISs) on surviving high-rises redirect signals. The key challenge is communication-limited partial observability, leaving each UAV with a narrow, fast-changing neighborhood view that destabilizes value estimation. Existing multi-agent reinforcement learning (MARL) approaches are inadequate--non-communication methods rely on unavailable global critics, heuristic sharing is brittle and redundant, and learnable protocols (e.g., CommNet, DIAL) lose per-neighbor structure and aggravate non-stationarity under tight bandwidth. To address partial observability, we propose a spatiotemporal A2C where each UAV transmits prior-decision messages with local state, a compact policy fingerprint, and a recurrent belief, encoded per neighbor and concatenated. A spatial discount shapes value targets to emphasize local interactions, while analysis under one-hop-per-slot latency explains stable training with delayed views. Experimental results show our policy outperforms IA2C, ConseNet, FPrint, DIAL, and CommNet--achieving faster convergence, higher asymptotic reward, reduced Temporal-Difference(TD)/advantage errors, and a better communication throughput-energy trade-off.
Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While multi-agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language-Augmented Multi-Agent Policy), a framework that integrates language into economic decision-making and narrows the gap to real-world settings. LAMP follows a Think-Speak-Decide pipeline: (1) Think interprets numerical observations to extract short-term shocks and long-term trends, caching high-value reasoning trajectories; (2) Speak crafts and exchanges strategic messages based on reasoning, updating beliefs by parsing peer communications; and (3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language-augmented decision-making. Experiments in economic simulation show that LAMP outperforms both MARL and LLM-only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrate the potential of language-augmented policies to deliver more effective and robust economic strategies.
This work investigates resource optimization in heterogeneous satellite clusters performing autonomous Earth Observation (EO) missions using Reinforcement Learning (RL). In the proposed setting, two optical satellites and one Synthetic Aperture Radar (SAR) satellite operate cooperatively in low Earth orbit to capture ground targets and manage their limited onboard resources efficiently. Traditional optimization methods struggle to handle the real-time, uncertain, and decentralized nature of EO operations, motivating the use of RL and Multi-Agent Reinforcement Learning (MARL) for adaptive decision-making. This study systematically formulates the optimization problem from single-satellite to multi-satellite scenarios, addressing key challenges including energy and memory constraints, partial observability, and agent heterogeneity arising from diverse payload capabilities. Using a near-realistic simulation environment built on the Basilisk and BSK-RL frameworks, we evaluate the performance and stability of state-of-the-art MARL algorithms such as MAPPO, HAPPO, and HATRPO. Results show that MARL enables effective coordination across heterogeneous satellites, balancing imaging performance and resource utilization while mitigating non-stationarity and inter-agent reward coupling. The findings provide practical insights into scalable, autonomous satellite operations and contribute a foundation for future research on intelligent EO mission planning under heterogeneous and dynamic conditions.
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: StarCraftII 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.
Connected and autonomous vehicles across land, water, and air must often operate in dynamic, unpredictable environments with limited communication, no centralized control, and partial observability. These real-world constraints pose significant challenges for coordination, particularly when vehicles pursue individual objectives. To address this, we propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations. This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations. We validate our approach in complex multi-agent navigation tasks featuring obstacles and dynamic agent populations. Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines. Moreover, task performance remains stable as the number of agents increases, demonstrating scalability. These findings highlight the potential of decentralized, goal-driven MARL to support effective coordination in realistic multi-vehicle systems operating across diverse domains.
Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations.
Multi-Agent Reinforcement Learning (MARL) has gained significant interest in recent years, enabling sequential decision-making across multiple agents in various domains. However, most existing explanation methods focus on centralized MARL, failing to address the uncertainty and nondeterminism inherent in decentralized settings. We propose methods to generate policy summarizations that capture task ordering and agent cooperation in decentralized MARL policies, along with query-based explanations for When, Why Not, and What types of user queries about specific agent behaviors. We evaluate our approach across four MARL domains and two decentralized MARL algorithms, demonstrating its generalizability and computational efficiency. User studies show that our summarizations and explanations significantly improve user question-answering performance and enhance subjective ratings on metrics such as understanding and satisfaction.
Despite the advantages of multi-agent reinforcement learning (MARL) for wireless use case such as medium access control (MAC), their real-world deployment in Internet of Things (IoT) is hindered by their sample inefficiency. To alleviate this challenge, one can leverage model-based reinforcement learning (MBRL) solutions, however, conventional MBRL approaches rely on black-box models that are not interpretable and cannot reason. In contrast, in this paper, a novel causal model-based MARL framework is developed by leveraging tools from causal learn- ing. In particular, the proposed model can explicitly represent causal dependencies between network variables using structural causal models (SCMs) and attention-based inference networks. Interpretable causal models are then developed to capture how MAC control messages influence observations, how transmission actions determine outcomes, and how channel observations affect rewards. Data augmentation techniques are then used to generate synthetic rollouts using the learned causal model for policy optimization via proximal policy optimization (PPO). Analytical results demonstrate exponential sample complexity gains of causal MBRL over black-box approaches. Extensive simulations demonstrate that, on average, the proposed approach can reduce environment interactions by 58%, and yield faster convergence compared to model-free baselines. The proposed approach inherently is also shown to provide interpretable scheduling decisions via attention-based causal attribution, revealing which network conditions drive the policy. The resulting combination of sample efficiency and interpretability establishes causal MBRL as a practical approach for resource-constrained wireless systems.
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents' current sub-trajectories, inform decision-making. During decentralized execution, we introduce a novel memory mechanism that effectively balances test-time online data with offline memory. Based on the constructed memory, we propose a hybrid utility score that incorporates both individual- and team-level returns, ensuring credit assignment across agents. Extensive experiments on cooperative MARL benchmarks, including Level-Based Foraging (LBF) and SMAC (v1/v2), show that MAICC enables faster adaptation to unseen tasks compared to existing methods. Code is available at https://github.com/LAMDA-RL/MAICC.
Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max (IGM) consistency, existing methods either enforce monotonicity constraints, which limit expressive power, or adopt softer surrogates at the cost of algorithmic complexity. In this work, we present a dynamical systems analysis of non-monotonic value decomposition, modeling learning dynamics as continuous-time gradient flow. We prove that, under approximately greedy exploration, all zero-loss equilibria violating IGM consistency are unstable saddle points, while only IGM-consistent solutions are stable attractors of the learning dynamics. Extensive experiments on both synthetic matrix games and challenging MARL benchmarks demonstrate that unconstrained, non-monotonic factorization reliably recovers IGM-optimal solutions and consistently outperforms monotonic baselines. Additionally, we investigate the influence of temporal-difference targets and exploration strategies, providing actionable insights for the design of future value-based MARL algorithms.
Multi-Agent Systems (MAS) have emerged as a powerful paradigm for modeling complex interactions among autonomous entities in distributed environments. In Multi-Agent Reinforcement Learning (MARL), communication enables coordination but can lead to inefficient information exchange, since agents may generate redundant or non-essential messages. While prior work has focused on boosting task performance with information exchange, the existing research lacks a thorough investigation of both the appropriate definition and the optimization of communication protocols (communication topology and message). To fill this gap, we introduce a generalized framework for learning multi-round communication protocols that are both effective and efficient. Within this framework, we propose three novel Communication Efficiency Metrics (CEMs) to guide and evaluate the learning process: the Information Entropy Efficiency Index (IEI) and Specialization Efficiency Index (SEI) for efficiency-augmented optimization, and the Topology Efficiency Index (TEI) for explicit evaluation. We integrate IEI and SEI as the adjusted loss functions to promote informative messaging and role specialization, while using TEI to quantify the trade-off between communication volume and task performance. Through comprehensive experiments, we demonstrate that our learned communication protocol can significantly enhance communication efficiency and achieves better cooperation performance with improved success rates.
In this paper, we propose capturing and utilizing \textit{Temporal Information through Graph-based Embeddings and Representations} or \textbf{TIGER} to enhance multi-agent reinforcement learning (MARL). We explicitly model how inter-agent coordination structures evolve over time. While most MARL approaches rely on static or per-step relational graphs, they overlook the temporal evolution of interactions that naturally arise as agents adapt, move, or reorganize cooperation strategies. Capturing such evolving dependencies is key to achieving robust and adaptive coordination. To this end, TIGER constructs dynamic temporal graphs of MARL agents, connecting their current and historical interactions. It then employs a temporal attention-based encoder to aggregate information across these structural and temporal neighborhoods, yielding time-aware agent embeddings that guide cooperative policy learning. Through extensive experiments on two coordination-intensive benchmarks, we show that TIGER consistently outperforms diverse value-decomposition and graph-based MARL baselines in task performance and sample efficiency. Furthermore, we conduct comprehensive ablation studies to isolate the impact of key design parameters in TIGER, revealing how structural and temporal factors can jointly shape effective policy learning in MARL. All codes can be found here: https://github.com/Nikunj-Gupta/tiger-marl.
As Multi Agent Reinforcement Learning systems are used in safety critical applications. Understanding why agents make decisions and how they achieve collective behavior is crucial. Existing explainable AI methods struggle in multi agent settings. They fail to attribute collective outcomes to individuals, quantify emergent behaviors, or capture complex interactions. We present MACIE Multi Agent Causal Intelligence Explainer, a framework combining structural causal models, interventional counterfactuals, and Shapley values to provide comprehensive explanations. MACIE addresses three questions. First, each agent's causal contribution using interventional attribution scores. Second, system level emergent intelligence through synergy metrics separating collective effects from individual contributions. Third, actionable explanations using natural language narratives synthesizing causal insights. We evaluate MACIE across four MARL scenarios: cooperative, competitive, and mixed motive. Results show accurate outcome attribution, mean phi_i equals 5.07, standard deviation less than 0.05, detection of positive emergence in cooperative tasks, synergy index up to 0.461, and efficient computation, 0.79 seconds per dataset on CPU. MACIE uniquely combines causal rigor, emergence quantification, and multi agent support while remaining practical for real time use. This represents a step toward interpretable, trustworthy, and accountable multi agent AI.
Weakly electric fish, like Gnathonemus petersii, use a remarkable electrical modality for active sensing and communication, but studying their rich electrosensing and electrocommunication behavior and associated neural activity in naturalistic settings remains experimentally challenging. Here, we present a novel biologically-inspired computational framework to study these behaviors, where recurrent neural network (RNN) based artificial agents trained via multi-agent reinforcement learning (MARL) learn to modulate their electric organ discharges (EODs) and movement patterns to collectively forage in virtual environments. Trained agents demonstrate several emergent features consistent with real fish collectives, including heavy tailed EOD interval distributions, environmental context dependent shifts in EOD interval distributions, and social interaction patterns like freeloading, where agents reduce their EOD rates while benefiting from neighboring agents' active sensing. A minimal two-fish assay further isolates the role of electro-communication, showing that access to conspecific EODs and relative dominance jointly shape foraging success. Notably, these behaviors emerge through evolution-inspired rewards for individual fitness and emergent inter-agent interactions, rather than through rewarding agents explicitly for social interactions. Our work has broad implications for the neuroethology of weakly electric fish, as well as other social, communicating animals in which extensive recordings from multiple individuals, and thus traditional data-driven modeling, are infeasible.
In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose Adaptive Regularized Multi-Agent Soft Actor-Critic (ARAC), which integrates an attention-based graph neural network (GNN) for modeling agent dependencies with an adaptive divergence regularization mechanism. The GNN enables expressive representation of spatial relations and state features in graph environments. Divergence regularization can serve as policy guidance to alleviate the sparse reward problem, but it may lead to suboptimal convergence when the reference policy itself is imperfect. The adaptive divergence regularization mechanism enables the framework to exploit reference policies for efficient exploration in the early stages, while gradually reducing reliance on them as training progresses to avoid inheriting their limitations. Experiments in pursuit and confrontation scenarios demonstrate that ARAC achieves faster convergence, higher final success rates, and stronger scalability across varying numbers of agents compared with MARL baselines, highlighting its effectiveness in complex graph-structured environments.