The proposed Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine and a MILP-Guided Navigation optimizer, is proposed, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.
Abstract
Zero-dimensional reduced-order models (0D ROMs) are central to multi-dimensional design workflows for high-end complex equipment. However, the planning process currently relies on manual expertise, limiting topological exploration and prolonging iterations. Even traditional optimization methods such as Genetic Algorithms (GA) are typically confined to local parameter tuning. Although Large Language Model (LLM) agents have shown promise in exploring large sample spaces, and frameworks such as Chain of Thought (CoT) and Reason and Act (ReAct) improve reasoning reliability, while Retrieval-Augmented Generation (RAG) overcomes domain knowledge barriers, a single agent still falls short for the long-horizon and highly coupled nature of complex 0D ROM planning. This paper proposes the Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine (SAGE) and a MILP-Guided Navigation (MGN) optimizer. Its core innovation is a dedicated graph representation method that accurately encodes the 0D flow network topology, converting the empirical planning process into a rigorous graph structure optimization problem. We validate the forward and inverse design capabilities and generalization performance of Z-COPA on two real aircraft engine secondary-air systems, two IEEE power-distribution reconfiguration benchmarks, and two water-distribution network benchmarks. The results show superior task completion quality, obtaining the best performance in both forward and reverse design of air systems. Z-COPA disrupts the traditional 0D model planning paradigm, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.
Multi-task multi-agent reinforcement learning (MT-MARL) aims to develop a single model capable of solving a diverse set of tasks. However, existing methods often fall short due to the substantial variation in optimal policies across tasks, making it challenging for a single policy model to generalize effectively. In contrast, we find that many tasks exhibit bounded similarity in their underlying dynamics—highly similar within certain groups (e.g., door-open/close) diverge significantly between unrelated tasks (e.g., door-open & object-catch). To leverage this property, we reconsider the role of modularity in multi-task learning, and propose M3W , a novel approach that applies mixture-of-experts (MoE) to world model instead of policy, enabling both learning and planning. For learning, it uses a SoftMoE-based dynamics model alongside a SparseMoE-based predictor to facilitate knowledge reuse across similar tasks while avoiding gradient conflicts across dissimilar tasks. For planning, it evaluates and optimizes actions using the predicted rollouts from the world model, without relying directly on a explicit policy model, thereby overcoming the limitations of policy-centric methods. As the first MoE-based multi-task world model, M3W demonstrates superior performance, sample efficiency, and multi-task adaptability, as validated on Bi-DexHands with 14 tasks and MA-Mujoco with 24 tasks. The code are available at https://github.
Zijie Zhao, Zhongyue Zhao, Kaixuan Xu et al.· Neural Information Processin...· 8 citations
: This paper provides a thorough survey and integrative presentation of cooperative path planning for multi-robot systems operating in dynamic, cluttered, and partially observable environments. People synthesise algorithmic foundations ranging from heuristic graph search to sampling-based motion planners, including A*, D* Lite, and Safe Interval Path Planning for discrete/time-augmented spaces, as well as RRT, RRT*, and Informed RRT* for continuous configuration spaces. Multi-agent coordination techniques are reviewed, covering reciprocal collision avoidance (ORCA) and centralised Multi-Agent Path Finding (MAPF) solvers such as Conflict-Based Search (CBS) and bounded-suboptimal variants (ECBS). The paper also examine control and safety layers like Model Predictive Control and Control Barrier Functions that translate plans into dynamically feasible commands with safety guarantees. Recent progress in cooperative multi-agent reinforcement learning (MAPPO, QMIX, MADDPG) is evaluated for adaptability under partial observability and nonstationary environments. Applications in warehousing, intelligent transportation, and disaster response are used to illustrate practical trade-offs and integration patterns, referencing real-world systems such as Kiva-style warehouse fleets and autonomous driving pipelines. The paper concludes with a focused discussion on open challenges — scalability with guarantees, safety under uncertainty, sim-to-real transfer, and planning – control interface fragility — and proposes research directions including learning-augmented heuristics, unified safety-aware planning, adaptive MPC – CBF filters, and more informative benchmarks to drive reproducible progress.
Yun Pan· Proceedings of the 3rd Inter...· 0 citations
Low-thrust trajectory optimization is a core technology in deep-space mission design. Indirect methods based on Pontryagin's Minimum Principle (PMP) offer rigorous optimality guarantees, yet their practical application faces three bottlenecks: (1) transversality conditions must be derived case by case for each constraint type; (2) different dynamics models require repeated code rewrites; and (3) shooting equations are highly sensitive to initial guesses. This paper presents HELIOS (Heuristic Engine for Low-thrust Interplanetary Optimization System), a trajectory optimization agent built around a large language model (LLM). Given a physical problem described in natural language, the system autonomously performs PMP symbolic derivation, SymPy verification, C++ shooting-code generation, and numerical solution without human intervention. Key innovations include: (1) a constraint-adaptive derivation framework that unifies arbitrary constraints into psi(x,p)=0 form and automatically generates stationarity conditions for free parameters (e.g., gravity-assist turning angle); (2) dynamics-adaptive four-module code generation supporting non-standard dynamics (solar sail, J2 perturbation) without modifying the underlying template; and (3) a general derivation rule set covering critical error-prone points in PMP derivation. Experiments on 11 progressive test scenarios show that HELIOS correctly derives and solves problems from simple rendezvous (8 variables) to multi-leg stay transfers (48 variables), gravity-assist trajectories (17 variables), and solar-sail minimum-time transfers (8 variables). The best compilation success rate reaches 100% (11/11). A multi-model comparison (8 open-source LLM backends, total scores 250-905) verifies the model-agnostic architecture and reveals a positive correlation between model scale and derivation capability.
Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capabilities to decompose these objectives into actionable plans. However, effectively grounding this high-level reasoning in physical multi-robot execution remains an open challenge. Existing LLM-based approaches fall mainly into two categories: Single-robot methods achieve robust contact-rich manipulation but lack the coordination mechanisms required for tasks spanning multiple workspaces. Current multi-robot frameworks focus on high-level planning, often treating manipulation as an idealized primitive that fails to account for real-world execution uncertainties. To address this, we propose a hierarchical closed-loop agentic LLM-based framework to ensure robust multi-robot manipulation. Our system consists of three specialized agents: the Planning Agent decomposes instructions into allocated sub-tasks, the Manipulation Agent for each robot executes actions via adaptive tool use, and the Verification Agent closes the loop by monitoring physical outcomes and feeding back semantic corrections. Extensive real-world experiments demonstrate that our framework achieves superior success rates, ensures robust adaptability ranging from single to cross workspace manipulation, and offers a generalizable approach for diverse manipulation tasks.
Yi-Xiang He, Lan Wei, Haoming Cen et al.· Robotics· 0 citations
This letter addresses the collision-free planning problem for heterogeneous multi-agent systems. Heterogeneity primarily refers to two aspects: differences in geometric configurations and variations in kinematic models. For non-point-mass agent models, it is essential to consider both geometric constraints arising from their physical dimensions and kinematic constraints. The proposed planning algorithm is an improvement upon the Conflict-Based Search (CBS) framework, consisting of high-level conflict detection and low-level single-agent path planning. The low-level planner employs a bidirectional space-time Hybrid A* algorithm (BSH) to accommodate the requirements of different kinematic models. The high-level planner introduces the concept of geometric envelopes to design conflict detection and constraint resolution methods in continuous space, effectively handling collision detection and conflict resolution among heterogeneous agents. To alleviate the computational burden caused by the high dimensionality of the search tree in CBS-like algorithms, a heuristic high-level node selection strategy is also proposed. Experimental results demonstrate that, compared to priority-based planning methods, the proposed approach yields more cost-effective planning solutions but more computational overhead while exhibiting an efficiency-optimality trade-off.
Jianing Hu, Weiran Yao, Haoyu Tian et al.· IEEE Robotics and Automation...· 0 citations
Ambient Assisted Living (AAL) environments aim to enable older people to remain active and lead an autonomous and independent life for as long as possible. Among the technologies that can be incorporated into these settings, socially assistive robots (SAR) seek to establish a more natural and intuitive means of interaction with people, whilst helping them to carry out everyday tasks. One of the main challenges facing the design of these robots is how to enable them to undertake more complex tasks. Recent advances in Large Language Models (LLMs) have opened new avenues for flexible robot deliberation, yet their integration into real-time robotic systems remains challenging due to latency constraints, reasoning reliability, and the complexity of coordinating multi-step tasks. This paper proposes a hierarchical multi-agent architecture for robot deliberation that addresses these challenges by combining LLM-based planning with structured execution mechanisms within the ROS 2 ecosystem. The proposed architecture employs a supervisor agent that decomposes high-level natural language instructions into prioritised subtasks, enabling a priority-driven execution model that dynamically adapts to task relevance, temporal constraints, and environmental feedback. Subtasks are delegated to a set of Single-Purpose Agents (SPAs), orchestrated via LangGraph state machines and coordinated through a priority-aware scheduling mechanism. A key design principle is the use of Behaviour Trees (BTs) as high-level callable tools through the Model Context Protocol (MCP), encapsulating closed-loop control strategies while enabling preemptive and priority-consistent execution. This reduces the number of LLM inference steps required per task and improves robustness under dynamic conditions. A further contribution concerns the deployment of fine-tuned, lightweight LLMs—on the order of 0.6 billion parameters—specifically adapted for both the supervisor and the individual SPA roles through parameter-efficient low-rank adaptation (LoRA). These models are trained on role-specific tool-calling datasets to specialise in constrained reasoning patterns and task-specific decision-making, enabling efficient, low-latency inference directly on edge hardware. The combination of fine-tuning and hierarchical priority control enhances both the determinism and responsiveness of the system while mitigating error propagation across agent interactions. The paper presents the full software architecture, a formal characterisation of the system as a priority-aware hierarchical policy over a graph of agent workflows, and an experimental evaluation in an Ambient Assisted Living scenario assessing task success rate, inference efficiency, responsiveness under competing priorities, and overall user experience. Because SPA execution is decoupled from the supervisor’s own reasoning loop, the architecture is designed to keep accepting, processing, and queuing new user queries while previously dispatched SPAs are still executing their tasks.
Alberto J. Tudela, Óscar Pons, José Galeas et al.· Applied Sciences· 0 citations