Graph-Based Task Allocation for Multi-Agent Fleet Management: A Genetic Algorithm Approach with LLM Integration

Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. To address this, we take inspiration from the human brain, in which planning is accomplished via component processes that are predominantly associated with specific brain regions. These processes include conflict monitoring, state prediction, state evaluation, task decomposition, and task coordination. We find that LLMs are often capable of carrying out these functions in isolation, but struggle to autonomously coordinate them in the service of a goal. Therefore, we propose a modular agentic architecture - the Modular Agentic Planner (MAP) - in which planning is performed via the interaction of specialized brain-inspired LLM modules. We evaluate MAP on three challenging planning tasks - graph traversal, Tower of Hanoi, and the PlanBench benchmark - as well as an NLP task requiring multi-step reasoning (strategyQA). We find that MAP yields significant improvements over both standard LLM methods and competitive agentic baselines, can be effectively combined with smaller and more cost-efficient LLMs, and displays superior transfer across tasks. These results demonstrate the benefit of utilizing knowledge from cognitive neuroscience to improve planning in LLMs.

Accurate interpretation of clinical test results is essential for diagnosing and managing complex immunological disorders. We explored the potential of large language models (LLMs) to automate interpretative reports for immunodeficiency and immune competence assessment via quantitative lymphocyte profiling and B-cell subset phenotyping (QLP/BSP). An LLM was fine-tuned using parameter-efficient techniques on a dataset consisting of immunophenotyping test results and corresponding interpretive reports. Model performance was compared against a retrieval-based method and expert pathologist reports. A novel automated evaluation framework assessed both the accuracy of cell population comments and the clinical relevance of generated interpretations. A custom application was built to simulate clinical workflows and measure the impact on pathologist efficiency and accuracy. Fine-tuned LLMs achieved accuracy comparable to expert pathologists in identifying and commenting on abnormal cell type counts and frequencies, in comparison the retrieval-based method exhibited substantial error rates. There was no significant difference between the rate at which abnormalities for cell subtypes were commented on between the LLMs and pathologists. More importantly, LLMs significantly reduced the time required for a single pathologist to finalize reports with a mean reduction in time of 29%. Our results suggest that LLMs hold promise for enhancing efficiency and consistency in the clinical laboratory setting. By automating aspects of interpretive reporting, LLMs can potentially reduce pathologist workload and improve the turnaround time for critical diagnostic information, while requiring expert pathologist oversight.

Large language models have found utility in the domain of robot task planning and task decomposition. Nevertheless, the direct application of these models for instructing robots in task execution is not without its challenges. Limitations arise in handling more intricate tasks, encountering difficulties in effective interaction with the environment, and facing constraints in the practical executability of machine control instructions directly generated by such models. In response to these challenges, this research advocates for the implementation of a multi-layer large language model to augment a robot's proficiency in handling complex tasks. The proposed model facilitates a meticulous layer-by-layer decomposition of tasks through the integration of multiple large language models, with the overarching goal of enhancing the accuracy of task planning. Within the task decomposition process, a visual language model is introduced as a sensor for environment perception. The outcomes of this perception process are subsequently assimilated into the large language model, thereby amalgamating the task objectives with environmental information. This integration, in turn, results in the generation of robot motion planning tailored to the specific characteristics of the current environment. Furthermore, to enhance the executability of task planning outputs from the large language model, a semantic alignment method is introduced. This method aligns task planning descriptions with the functional requirements of robot motion, thereby refining the overall compatibility and coherence of the generated instructions. To validate the efficacy of the proposed approach, an experimental platform is established utilizing an intelligent unmanned vehicle. This platform serves as a means to empirically verify the proficiency of the multi-layer large language model in addressing the intricate challenges associated with both robot task planning and execution.

Large Language Models (LLMs) have emerged as a promising alternative to traditional static program analysis methods, such as symbolic execution, offering the ability to reason over code directly without relying on theorem provers or SMT solvers. However, LLMs are also inherently approximate by nature, and therefore face significant challenges in relation to the accuracy and scale of analysis in real-world applications. Such issues often necessitate the use of larger LLMs with higher token limits, but this requires enterprise-grade hardware (GPUs) and thus limits accessibility for many users. In this paper, we propose LLM-based symbolic execution —a novel approach that enhances LLM inference via a path-based decomposition of the program analysis tasks into smaller (more tractable) subtasks. The core idea is to generalize path constraints using a generic code-based representation that the LLM can directly reason over, and without translation into another (less-expressive) formal language. We implement our approach in the form of AutoBug, an LLM-based symbolic execution engine that is lightweight and language-agnostic, making it a practical tool for analyzing code that is challenging for traditional approaches. We show that AutoBug can improve both the accuracy and scale of LLM-based program analysis, especially for smaller LLMs that can run on consumer-grade hardware.

Institutional agencies play a crucial role in land use change, but modelling their decision-making processes is challenging due to the complexity of the environment they operate within and the bounded rationality of human organizations. Large Language Models (LLMs) offer a novel approach to simulating human decisions. This paper aims to investigate the challenges and opportunities that LLMs bring to land use change modelling by integrating LLM-powered institutional agents with the CRAFTY land use model, in which land users produce a range of ecosystem services. The study develops a structured prompt development approach for coupling LLM-powered agents with existing large-scale simulations. Four types of LLM-powered agents are examined, which use taxes to steer meat production toward a prescribed policy goal. The agents provide reasoning and policy action output in each simulation iteration. The study also uses a technique called quasi-multi-agent to simulate multiple roles involved in the policy processes. Unlike authentic multi-agent simulation, the LLM-powered quasi-multi-agent leverages the LLM's ability to generate contextually coherent text and allows the agents to work as a scriptwriter who composes conversations between different roles. This approach conserves computational resources and has the potential to manage conversational dynamics in policy discussions. The efficacy of these agents is benchmarked against two baseline scenarios: one without any policy intervention and another implementing optimal policy actions determined through a genetic algorithm. The findings show that while LLM-powered agents perform better than the non-intervention scenario, they fall short of the performance achieved by optimal policy actions. However, LLM-powered agents demonstrate human-like decision-making, marked by policy consistency and transparent reasoning. The agents also generate real-world policymaking strategies, including incrementalism, considering delayed policy influence, proactive policy adjustments, and balancing multiple stakeholder interests. Agents equipped with experiential learning capabilities excel in achieving policy objectives through progressive policy actions. The order of reasoning and proposed policy actions in the prompts has a notable effect on the agents' performance. The research points to both promising opportunities and significant challenges in integrating LLMs into large-scale land-use simulations. The opportunities include exploring naturalistic institutional decision-making and its impact on land use change, using LLM's information retrieval to handle massive institutional documents, modelling institutional networks, and human-AI cooperation. However, challenges mainly lie in the scalability and reliability of LLMs due to the dependence on LLM providers, the paradox of pursuing realistic institutional behaviours versus abstraction and simplification in existing models, and the effectiveness and efficiency in scrutinizing massive textual output, detecting illogical content in prompts, and inaccurate formatting.

Task allocation is an important problem in multi-robot systems, particularly in dynamic and unpredictable environments such as offshore oil platforms, large-scale factories, or disaster response scenarios, where high change rates, uncertain state transitions, and varying task demands challenge the predictability and stability of robot operations. Traditional static task allocation strategies often struggle to meet the efficiency and responsiveness demands of these complex settings, while optimization heuristics, though improving planning time, exhibit limited scalability. To address these limitations, this paper proposes a task allocation method based on the Monte Carlo Tree Search (MCTS) algorithm, which leverages the anytime property of MCTS to achieve a balance between fast response and continuous optimization. Firstly, the centralized adaptive MCTS algorithm generates preliminary solutions and monitors the state of the robots in minimal time. It utilizes dynamic Upper Confidence Bounds for Trees (UCT) values to accommodate varying task dimensions, outperforming the heuristic Multi-Robot Goal Assignment (MRGA) method in both planning time and overall task completion time. Furthermore, the parallelized distributed MCTS algorithm reduces algorithmic complexity and enhances computational efficiency through importance sampling and parallel processing. Experimental results demonstrate that the proposed method significantly reduces computation time while maintaining task allocation performance, decreasing the variance of planning results and improving algorithmic stability. Our approach enables more flexible and efficient task allocation in dynamically evolving and complex environments, providing robust support for the deployment of multi-robot systems.

Edge computing for machine learning has become a heated research topic. On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, one obstacle is that transfer learning imposes heavy computation burden to the resource-constrained edge devices. Motivated by the fact that only a few tasks of Multi-task Transfer Learning (MTL) have a higher potential for overall decision performance improvement, we design a novel task allocation scheme, which assigns more important tasks to more powerful edge devices to maximize the overall decision performance. In this paper, we focus on task allocation under multi-task scenarios by introducing task importance and make the following contributions. First, we reveal that it is important to measure the impact of tasks on overall decision performance improvement and quantify task importance. We also observe the long-tail property of task importance, i.e., only a few tasks are important, which facilitates more efficient task allocation. Second, we show that task allocation with task importance for MTL (TATIM) is in fact a variant of the NP-complete Knapsack problem, where the complicated computation to solve this problem needs to be conducted repeatedly under varying contexts. To solve TATIM with high computational efficiency, we innovatively propose a Data-driven Cooperative Task Allocation (DCTA) approach. Third, we evaluate the performance of our DCTA approach by applying it to a real-world industrial operation (e.g., AIOps) scenario. Experiments show that our DCTA approach can reduce 3.24 times of processing time compared with the state-of-the-art when solving TATIM. We offer our DCTA approach as an effective and practical mechanism for reducing the required resource associated with performing MTL on edge devices.

Task decomposition and allocation problems and discrete event systems

To realize the efficient decomposition and allocation of collaborative production tasks and resources among multiple enterprises, a task decomposition and allocation model for collaborative production among multiple manufacturing enterprises is proposed in a big data environment. The model is designed for the efficient and fast processing of production information using big data technology. This study innovatively applies the 5S management method to conduct data preprocessing for a manufacturing service provider and design the operation process of data cleaning and conversion to improve the efficiency of data processing. A collaborative optimization model, based on a hierarchical model with seven levels and considering time, costs, and services, is established for the task of production to achieve a reasonable match between supply and demand. Finally, the correlation coefficients of manufacturing service providers are configured according to weight order, so that the weight order is symmetrical with that of the manufacturer. The model also engages all manufacturing service providers with different production capabilities in collaborative production. The model is proved to be scientific and effective by using a specific example. In cooperative production activities, the production tasks of small and medium-sized enterprises can be effectively allocated. It can also realize efficient cooperative production among multiple manufacturing enterprises.

Cooperative task allocation and decision are important aspects of networks that involve heterogeneous nodes operating in ad hoc mode like flying ad hoc networks (FANETs). The task allocation can be either mission based or simple utilization of available resources. In networks, including mission critical resources, cooperative task allocation and rendezvous are the key factors that drive the mission as well as optimize the performance. Many optimization algorithms have been designed and developed which focus on the cooperative behavior of nodes and also handle resources efficiently. Cooperative allocation and rendezvous both can be achieved by taking an example from biological world. In this paper, a new hill Myna and desert Sparrow optimization algorithm, namely HMADSO, is proposed for cooperative rendezvous and efficient task allocation. The application and analysis of proposed algorithm are shown for FANETs. To validate the proposed HMADSO, onboard processors, as well as simulation-based analysis, are carried out. The libraries for the proposed approach are provided at http://bit.ly/HMADSOcode .

The growing administrative burden on clinicians, particularly in medical documentation, contributes to burnout and may compromise patient safety. Recent advancements in generative artificial intelligence (AI) offer a promising solution to improve documentation processes and address these challenges. This study aims to evaluate the feasibility of using a fine-tuned OpenAI Curie model to automate the generation of medical report summaries (epicrises) in ophthalmology. By assessing the model's performance through human and automated evaluations, this study seeks to determine its potential for reducing clinician workload while ensuring accuracy, usefulness, and compliance with regulatory requirements. A data set of around 60,000 anonymized medical letters was created using a custom algorithm to comply with General Data Protection Regulation guidelines. The Curie model was fine-tuned on this data set to generate epicrises from medical histories, diagnoses, and findings. The performance evaluation involved various human assessments and automated evaluations from 2 large language models (LLMs). In the clinical context, 49.9% (384/769) of epicrises were evaluated as helpful or excellent, whereas only 25% (194/769) were considered disturbing. In a human (manual) evaluation, formal correctness was rated significantly higher than the neutral midpoint of 2.5 on the 4-point rating scale, as determined by a 1-sample Wilcoxon signed-rank test (mean 3.59, SD 0.85; W=1686; P<.001). Using paired t tests, we found a significant reduction in time, as correcting an AI epicrisis was faster than manually writing one (mean 109.52, SD 53.30 vs mean 54.25, SD 63.34 s; t68=3.39; P<.01). While medical accuracy and usefulness showed positive trends, these did not reach statistical significance when compared to the neutral midpoint (for medical accuracy, W= 7456; P=.08), for usefulness, W=7652.5; P=.18). Epicrises generated or corrected with AI were significantly shorter than manually written ones (mean 330.43, SD 115.42 vs mean 501.07, SD 243.50 characters; t68=-6.10; P<.001). Automated LLM assessments showed alignment with human ratings, with over 52% (356/679) and 66% (489/743) of responses in the top agreement categories, respectively. This supports overall consistency, though the comparison remains a proof of concept given methodological limitations. Our study demonstrates the technical and practical feasibility of introducing fine-tuned commercial LLMs into clinical practice. The AI-generated epicrises were formally and clinically correct in many cases and showed time-saving potential. While medical accuracy and usefulness varied across cases and should be focused on in further developments, a significant workload reduction is likely. Our anonymization process showed that regulatory challenges in the context of AI with patient data can effectively be dealt with. In summary, this study highlights the promise of transformer-based LLMs in reducing administrative tasks in health care. It outlines a pipeline for integrating LLMs into European Union clinical practice, emphasizing the need for careful implementation to ensure efficiency and patient safety.

An AI assistant to help review and improve causal reasoning in epidemiological documents

Performing complex tasks in open environments remains challenging for robots, even when using large language models (LLMs) as the core planner. Many LLM‐based planners are inefficient due to their large number of parameters and prone to inaccuracies because they operate in open‐loop systems. We think the reason is that only applying LLMs as planners is insufficient. In this study, we propose Dadu‐Embodied ( Dadu‐E) , a robust closed‐loop planning framework for embodied Artificial Intelligence (AI) robots. Specifically, Dadu‐E is equipped with a relatively lightweight LLM, a set of encapsulated robot skill instructions, a robust feedback system, and memory augmentation. Together, these components enable Dadu‐E to (i) actively perceive and adapt to dynamic environments, (ii) optimize computational costs while maintaining high performance, and (iii) recover from execution failures using its memory and feedback mechanisms. By seamlessly integrating a lightweight LLM, encapsulated robot skill instructions, closed‐loop feedback, and memory augmentation, Dadu‐E establishes a robust and extensible embodied AI robotic framework capable of stable operation in real‐world environments. Extensive experiments on real‐world and simulated tasks show that Dadu‐E achieves task success rates comparable to embodied AI robots with larger models as planners like COME‐Robot, while reducing computational requirements by . Users are encouraged to explore our system at https://rlc-lab.github.io/dadu-e/ .

We consider the problem of warehouse multi-robot automation system in discrete-time and discrete-space configuration with focus on the task allocation and conflict-free path planning. We present a system design where a centralized server handles the task allocation and each robot performs local path planning distributively. A genetic-based task allocation algorithm is firstly presented, with modification to enable heuristic learning. A semi-complete potential field based local path planning algorithm is then proposed, named the recursive excitation/relaxation artificial potential field (RERAPF). A mathematical proof is also presented to show the semi-completeness of the RERAPF algorithm. The main contribution of this paper is the modification of conventional artificial potential field (APF) to be semi-complete while computationally efficient, resolving the traditional issue of incompleteness. Simulation results are also presented for performance evaluation of the proposed path planning algorithm and the overall system.

Fog computing has emerged as a potential solution to accommodate the explosive computational demand of mobile users. This potential mainly stems from the capacity of task offloading and allocation at the network edge, reducing the delay and improving the quality of service. However, optimizing the performance of a fog network is often challenging, when consider the distinct abilities and capacities of fog nodes. We study the distributed task allocation problem in such a heterogeneous fog computing network under noises. We formulate the problem as a social-concave game, where the players attempt to minimize their regret while converging to Nash equilibrium. We develop a no-regret strategy for task allocation. The strategy, namely bandit gradient ascent with momentum, is an online convex optimization algorithm with bandit feedback. Theoretical and numerical analysis show the superior performance of the proposed strategy for efficient task allocation compared to the state-of-the-art methods.