1 November 2019 in Artificial Intelligence in Medicine
20 February 2026 in IEEE Transactions on Computational Social Systems
Large language models (LLMs) have emerged as integral tools for reasoning, planning, and decision-making, drawing upon their extensive world knowledge and proficiency in language-related tasks. LLMs thus hold tremendous potential for natural language interaction within multiagent systems to foster cooperation. However, LLM agents tend to over-report and comply with any instruction, which may result in information redundancy and confusion in multiagent cooperation. Inspired by human organizations, this article introduces a framework that imposes prompt-based organization structures on LLM agents to mitigate these problems. Through a series of experiments with embodied LLM agents and human–agent collaboration, our results highlight the impact of designated leadership on team efficiency, shedding light on the leadership qualities displayed by LLM agents and their spontaneous cooperative behaviors. Further, we harness the potential of LLMs to propose enhanced organizational prompts, via a criticize-reflect process, resulting in novel organization structures that reduce communication costs and enhance team efficiency.
1 August 2018 in Knowledge-Based Systems
24 February 2017 in Industrial & Engineering Chemistry Research
8 July 2020 in Computers and Electrical Engineering
6 June 2017 in IISE Transactions
In this article, an iteration approach is introduced to study closed-loop production lines with a constant number of carriers. A Bernoulli machine reliability model is assumed. The closed-loop system is decomposed into multiple small loop lines and further down to two-machine loops, in which the distributions of carriers are derived. Then an iteration procedure is presented to estimate the interactions between the small loops to modify the carrier distributions. Upon convergence, the system production rate can be estimated using these distributions. The convergence of the procedure is proved analytically, and the accuracy of estimation is justified numerically. It is shown that the method has good accuracy and computational efficiency. In addition, a case study at an automotive assembly plant is introduced to illustrate the applicability of the method.