State of the Field
Recent advancements in multi-agent systems are addressing critical challenges in communication efficiency, orchestration, and resilience, making them more applicable to real-world scenarios. New frameworks are being developed to enhance bandwidth-efficient communication among agents, enabling effective coordination in environments with limited resources, such as robotic swarms and autonomous vehicle fleets. Additionally, innovative paradigms are shifting away from rigid, rule-based workflows to dynamic, agent-to-agent communication, allowing for more flexible task management and improved handling of complex scenarios. Research is also focusing on optimizing latency in parallel execution, which is crucial for time-sensitive applications. Moreover, the introduction of resilience optimization techniques aims to proactively design systems that can withstand perturbations, enhancing their robustness in distributed settings. Collectively, these developments signal a maturation of multi-agent systems, positioning them to tackle commercial problems in logistics, healthcare, and autonomous operations with greater efficiency and reliability.
Papers
1–10 of 21Learning Latency-Aware Orchestration for Parallel Multi-Agent Systems
Multi-agent systems (MAS) enable complex reasoning by coordinating multiple agents, but often incur high inference latency due to multi-step execution and repeated model invocations, severely limiting...
AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making
We introduce AgenticSimLaw, a role-structured, multi-agent debate framework that provides transparent and controllable test-time reasoning for high-stakes tabular decision-making tasks. Unlike black-b...
Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL
Most existing Large Language Model (LLM)-based Multi-Agent Systems (MAS) rely on predefined workflows, where human engineers enumerate task states in advance and specify routing rules and contextual i...
Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization
Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness. We present a framewo...
EvoSkill: Automated Skill Discovery for Multi-Agent Systems
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this th...
ResMAS: Resilience Optimization in LLM-based Multi-agent Systems
Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. However, MAS are typicall...
CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing
Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tas...
Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty
Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent ...
Differentiable Modal Logic for Multi-Agent Diagnosis, Orchestration and Communication
As multi-agent AI systems evolve from simple chatbots to autonomous swarms, debugging semantic failures requires reasoning about knowledge, belief, causality, and obligation, precisely what modal logi...
Lifelong Scalable Multi-Agent Realistic Testbed and A Comprehensive Study on Design Choices in Lifelong AGV Fleet Management Systems
We present Lifelong Scalable Multi-Agent Realistic Testbed (LSMART), an open-source simulator to evaluate any Multi-Agent Path Finding (MAPF) algorithm in a Fleet Management System (FMS) with Automate...