SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication

• URL: http://arxiv.org/abs/2605.27532v1
• Date: Tue, 26 May 2026 18:06:19 GMT
• Title: SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
• Abstract summary: We propose a self-supervised framework for learning compact, stable, and policy-relevant communication representations.<n>We show that the learned communication space yields improved stability, sample efficiency, and throughput under policy fine-tuning.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable communication protocols, ungrounded message semantics, and interference between communication learning and policy optimization, leading to degraded coordination over time. We propose SCALE-COMM (Shared, Contrastively-Aligned Latent Embeddings for COMMunication), a self-supervised framework for learning compact, stable, and policy-relevant communication representations. SCALE-COMM decouples communication learning from policy optimization by training low-dimensional latent messages that capture task-relevant planning and traffic information, while enforcing consistency across agents and time. Across standard MARL benchmarks and a realistic warehouse coordination task, SCALE-COMM consistently outperforms existing communication frameworks in both representation quality and task performance. The learned communication space yields improved stability, sample efficiency, and throughput under policy fine-tuning, demonstrating the effectiveness of representation-driven communication for scalable multi-agent coordination.

Related papers

• Robust and Efficient Communication for Multi-Agent Learning [1.7205106391379026]
  This paper introduces Multi-Agent Regularized Communication (MARC), a novel framework inspired by information-theoretic principles of conditional mutual information.<n>MARC employs an attention-based architecture coupled with a unique message regularization mechanism designed to minimize uncertainty regarding future system states.<n>Our results demonstrate that MARC significantly outperforms state-of-the-art methods in complex cooperative domains.
  arXiv  Detail & Related papers  (2026-09-14T10:44:11Z)
• Task-Oriented Sensing and Covert Transmissions for Collaborative Multi-AUV Systems [67.63956000297922]
  This paper proposes a Sensed Information Value Realization Multi-Agent Reinforcement Learning (SVR-MARL) framework to characterize the utility of information for cooperative tasks.<n>The potential of the proposed framework to improve collaborative task efficiency while reducing unnecessary communication and exposure risks is demonstrated.
  arXiv  Detail & Related papers  (2026-07-15T14:29:25Z)
• Communication Policy Evolution for Proactive LLM Agents [58.4960889232199]
  This paper formalizes Communication Policy, establishes textual and UI-based policies, and then evaluates communication policies across diverse environments.<n>We propose Communication Policy Evolution (CPE), a self-evolution framework for refining communication policies through rollout and prompt-level evolving.
  arXiv  Detail & Related papers  (2026-06-12T09:54:01Z)
• Multi-Agent Reinforcement Learning with Communication-Constrained Priors [22.124940712335434]
  Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems.<n>Existing multi-agent reinforcement learning with communication struggles to apply to complex and dynamic real-world environments.<n>We introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward.
  arXiv  Detail & Related papers  (2025-12-03T07:35:07Z)
• Robust and Efficient Communication in Multi-Agent Reinforcement Learning [18.405707681765453]
  Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents.<n>Most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments.<n>This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints.
  arXiv  Detail & Related papers  (2025-11-14T15:23:11Z)
• Learning to Interact in World Latent for Team Coordination [53.51290193631586]
  This work presents a novel representation learning framework, interactive world latent (IWoL), to facilitate team coordination in multi-agent reinforcement learning (MARL)<n>Our key insight is to construct a learnable representation space that jointly captures inter-agent relations and task-specific world information by directly modeling communication protocols.<n>Our representation can be used not only as an implicit latent for each agent, but also as an explicit message for communication.
  arXiv  Detail & Related papers  (2025-09-29T22:13:39Z)
• Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models [0.0]
  A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or learn them end-to-end.<n>We propose and compare two communication strategies for a cooperative task-allocation problem.<n>Our experiments reveal that while emergent communication is viable in simple settings, the engineered, world model-based approach shows superior performance, sample efficiency, and scalability as complexity increases.
  arXiv  Detail & Related papers  (2025-08-04T21:29:07Z)
• Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning [7.872846260392537]
  MARL-CPC is a framework that enables communication among fully decentralized, independent agents.<n>Unlike conventional methods that treat messages as part of the action space and assume cooperation, MARL-CPC links messages to state inference.<n> Benchmarks show thatBandit-CPC and IPPO-CPC outperform standard message-as-action approaches.
  arXiv  Detail & Related papers  (2025-05-28T05:23:47Z)
• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Learning Multi-Agent Communication from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. Our proposed approach, CommFormer, efficiently optimize the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-05-14T12:40:25Z)
• Learning Multi-Agent Communication with Contrastive Learning [3.816854668079928]
  We introduce an alternative perspective where communicative messages are considered as different incomplete views of the environment state. By examining the relationship between messages sent and received, we propose to learn to communicate using contrastive learning. In communication-essential environments, our method outperforms previous work in both performance and learning speed.
  arXiv  Detail & Related papers  (2023-07-03T23:51:05Z)
• Learning Structured Communication for Multi-agent Reinforcement Learning [104.64584573546524]
  This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology.
  arXiv  Detail & Related papers  (2020-02-11T07:19:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.