aiqbench analysis
OSDAG addresses the latency bottleneck in multi-robot systems by limiting Large Language Model usage to a single semantic parsing step, followed by an efficient online scheduler that manages task dependencies via a Directed Acyclic Graph. This architecture exposes parallel execution opportunities while maintaining correctness, significantly reducing reasoning time and overall task completion duration compared to dialogue-based or sequential planning methods. The approach demonstrates practical viability for coordinating heterogeneous robot fleets in complex, long-horizon scenarios without relying on continuous high-cost LLM inference loops.
OSDAG: Online Scheduling for Efficient Multi-Robot Collaboration
arXiv:2606.15255v2 Announce Type: replace Abstract: Coordinating heterogeneous multi-robot systems (MRS) for complex, long-horizon tasks requires both flexible high-level reasoning and efficient execution-time scheduling. Existing LLM-based approaches struggle to balance reasoning efficiency and execution flexibility. Flat sequential plans are efficient to generate but overlook parallel execution opportunities, while repeated LLM reasoning introduces high latency, and offline schedules may unnecessarily keep robots idle due to fixed execution orders. This paper presents OSDAG, a novel framework that resolves this trade-off by employing a Directed Acyclic Graph (DAG) as the central representation for multi-robot coordination, coupled with constraint-aware online scheduling. The LLM is typically invoked once as a semantic parser that decomposes a natural-language instruction into a dependency-annotated task graph encoding precedence relations, together with robot capability and resource-feasibility constraints. A lightweight online scheduler then dynamically dispatches dependency-ready tasks to their assigned robots as soon as they become idle, exposing available parallelism while preserving correctness. Experiments across five benchmark scenarios demonstrate that OSDAG achieves $5-15\times$ faster reasoning time than dialogue-based methods, reduces makespan by up to $38\%$ over sequential baselines, and maintains competitive success rates. Both simulation and real-world experiments on human-robot collaboration tasks validate the effectiveness and practicality of the proposed approach for efficient multi-robot coordination. The website and resources are available at http://thanhnguyencanh.github.io/LLM_DAG4MultiRobot
Abstract:Coordinating heterogeneous multi-robot systems (MRS) for complex, long-horizon tasks requires both flexible high-level reasoning and efficient execution-time scheduling. Existing LLM-based approaches struggle to balance reasoning efficiency and execution flexibility. Flat sequential plans are efficient to generate but overlook parallel execution opportunities, while repeated LLM reasoning introduces high latency, and offline schedules may unnecessarily keep robots idle due to fixed execution orders. This paper presents OSDAG, a novel framework that resolves this trade-off by employing a Directed Acyclic Graph (DAG) as the central representation for multi-robot coordination, coupled with constraint-aware online scheduling. The LLM is typically invoked once as a semantic parser that decomposes a natural-language instruction into a dependency-annotated task graph encoding precedence relations, together with robot capability and resource-feasibility constraints. A lightweight online scheduler then dynamically dispatches dependency-ready tasks to their assigned robots as soon as they become idle, exposing available parallelism while preserving correctness. Experiments across five benchmark scenarios demonstrate that OSDAG achieves $5-15\times$ faster reasoning time than dialogue-based methods, reduces makespan by up to $38\%$ over sequential baselines, and maintains competitive success rates. Both simulation and real-world experiments on human-robot collaboration tasks validate the effectiveness and practicality of the proposed approach for efficient multi-robot coordination. The website and resources are available at this http URL
Robotics (cs.RO)
arXiv:2606.15255 [cs.RO]
(or arXiv:2606.15255v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.15255 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 299 words
Related coverage
OSDAG: Online Scheduling for Efficient Multi-Robot Collaboration
arXiv · Jun 16, 2026
Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts
arXiv · Aug 25, 2026
Dynamic Multi-Agent Pickup and Delivery in Robotic Cellular Warehousing Systems
arXiv · Jun 5, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026