More Like this

1. Adaptive task planning and coordination in multi-agent manufacturing systems using large language models

   https://doi.org/10.1016/j.rcim.2026.103245  

   Lim, Jonghan; Zhao, Jiabao; Hernandez, Ezekiel; Kovalenko, Ilya (August 2026, Robotics and Computer-Integrated Manufacturing)

   As the demand for personalized products increases, manufacturing processes are becoming more complex due to greater variety and uncertainty in product requirements. Traditional manufacturing systems face challenges in adapting to product changes without manual interventions, leading to an increase in product delays and operational costs. Multi-agent manufacturing control systems, a decentralized framework consisting of collaborative agents, have been employed to enhance flexibility and adaptability in manufacturing. However, existing multi-agent system approaches are often initialized with predefined capabilities, limiting their ability to handle new requirements that were not modeled in advance. To address this challenge, this work proposes a large language model-enabled multi-agent framework that enables adaptive matching, translating new product requirements to manufacturing process control at runtime. A product agent, which is a decision-maker for a product, interprets unforeseen product requirements and matches with manufacturing capabilities by dynamically retrieving manufacturing knowledge during runtime. Communication strategies and a decision-making method are also introduced to facilitate adaptive task planning and coordination. The proposed framework was evaluated using an assembly task board testbed across three case studies of increasing complexity. Results demonstrate that the framework can process unforeseen product requirements into executable operations, dynamically discover manufacturing capabilities, and improve resource utilization. 

   more » « less
2. Multi-Agent Path Planning Under Observation Schedule Constraints

   https://doi.org/10.1109/IROS45743.2020.9340747  

   Yang, Ziqi; Tron, Roberto (October 2020, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS))

   null (Ed.)

   We consider the problem of enhanced security of multi-robot systems to prevent cyber-attackers from taking control of one or more robots in the group. We build upon a recently proposed solution that utilizes the physical measurement capabilities of the robots to perform introspection, i.e., detect the malicious actions of compromised agents using other members of the group. In particular, the proposed solution finds multi-agent paths on discrete spaces combined with a set of mutual observations at specific locations to detect robots with significant deviations from the preordained routes. In this paper, we develop a planner that works on continuous configuration spaces while also taking into account similar spatio-temporal constraints. In addition, the planner allows for more general tasks that can be formulated as arbitrary smooth cost functions to be specified. The combination of constraints and objectives considered in this paper are not easily handled by popular path planning algorithms (e.g., sampling-based methods), thus we propose a method based on the Alternating Direction Method of Multipliers (ADMM). ADMM is capable of finding locally optimal solutions to problems involving different kinds of objectives and non-convex temporal and spatial constraints, and allows for infeasible initialization. We benchmark our proposed method on multi-agent map exploration with minimum-uncertainty cost function, obstacles, and observation schedule constraints. 

   more » « less
3. Stable and Efficient Shapley Value-Based Reward Reallocation for Multi-Agent Reinforcement Learning of Autonomous Vehicles

   Songyang Han, He Wang (May 2022, 2022 IEEE International Conference on Robotics and Automation)

   With the development of sensing and communica- tion technologies in networked cyber-physical systems (CPSs), multi-agent reinforcement learning (MARL)-based methodolo- gies are integrated into the control process of physical systems and demonstrate prominent performance in a wide array of CPS domains, such as connected autonomous vehicles (CAVs). However, it remains challenging to mathematically characterize the improvement of the performance of CAVs with commu- nication and cooperation capability. When each individual autonomous vehicle is originally self-interest, we can not assume that all agents would cooperate naturally during the training process. In this work, we propose to reallocate the system’s total reward efficiently to motivate stable cooperation among autonomous vehicles. We formally define and quantify how to reallocate the system’s total reward to each agent under the proposed transferable utility game, such that communication- based cooperation among multi-agents increases the system’s total reward. We prove that Shapley value-based reward reallocation of MARL locates in the core if the transferable utility game is a convex game. Hence, the cooperation is stable and efficient and the agents should stay in the coalition or the cooperating group. We then propose a cooperative policy learning algorithm with Shapley value reward reallocation. In experiments, compared with several literature algorithms, we show the improvement of the mean episode system reward of CAV systems using our proposed algorithm. 

   more » « less
4. Trust-Aware Task Allocation With Quantum Optimization in Adversarial Multi-Agent Systems

   https://doi.org/10.1109/ICDMW69685.2025.00348  

   Barroso, Giselle Roman; Ho, Duy; Miller, Luke; Alanazi, Ahmed; Lee, Yugyung (November 2025, IEEE)

   This paper introduces a trust-aware task allocation framework for adversarial multi-agent systems, leveraging quantum optimization to improve decision-making under uncertainty. The approach models agent reliability and adversarial behavior through a trust-aware utility function, enabling robust and adaptive task assignment in dynamic environments. By incorporating quantum-inspired optimization techniques, the framework efficiently explores complex solution spaces that are difficult for classical methods. Experimental results demonstrate improved resilience to adversarial agents, enhanced allocation efficiency, and overall system robustness compared to baseline approaches. The proposed framework contributes to secure and scalable coordination in distributed systems, with applications in cybersecurity, autonomous systems, and networked sensing environments. 

   more » « less
5. LLM Collaboration with Multi-Agent Reinforcement Learning

   Liu, Shuo; Chen, Tianle; Liang, Zeyu; Lyu, Xueguang; Amato, Christopher (January 2026, The Annual AAAI Conference on Artificial Intelligence (AAAI))

   A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pre-trained independently and not specifically optimized for coordination. For example, existing LLM fine-tuning frameworks rely on individual rewards, which require complex reward designs for each agent to encourage collaboration. To address this challenge, we model LLM collaboration as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. We develop a multi-agent, multi-turn algorithm, MultiAgent Group Relative Policy Optimization (MAGRPO), to solve it, building on current RL approaches for LLMs as well as MARL techniques. Our experiments on LLM writing and coding collaboration demonstrate that fine-tuning multiple LLMs with MAGRPO enables agents to generate high-quality responses efficiently through effective cooperation. Our approach opens the door to using MARL methods for LLM collaboration and highlights the associated challenges. Our code is available at https://github.com/OpenMLRL/CoMLRL. 

   more » « less