Uploaded November 2026 | Updated November 2026, 1 day ago
In this work, we propose EFLUX, a context-aware, geometry-grounded LLM agentic framework for automatic and elastic multi-robot formation navigation. EFLUX extracts a structured scene representation and uses an LLM to reason jointly over both deformation actions (e.g., scaling and shearing) and reconfiguration actions (e.g., splitting and merging). These strategies are then translated into executable per-robot waypoints through a closed-loop generation, verification, and correction pipeline. Simulation and hardware experiments show that EFLUX enables safe, continuous, and elastic formation navigation in challenging scenarios, reducing deadlocks and failures while maintaining coherent multi-robot coordination.
Check our paper for more details: arxiv.org/abs/2607.12050
In this work, we propose EFLUX, a context-aware, geometry-grounded LLM agentic framework for automatic and elastic multi-robot formation navigation. EFLUX extracts a structured scene representation and uses an LLM to reason jointly over both deformation actions (e.g., scaling and shearing) and reconfiguration actions (e.g., splitting and merging). These strategies are then translated into executable per-robot waypoints through a closed-loop generation, verification, and correction pipeline. Simulation and hardware experiments show that EFLUX enables safe, continuous, and elastic formation navigation in challenging scenarios, reducing deadlocks and failures while maintaining coherent multi-robot coordination.
Check our paper for more details: arxiv.org/abs/2607.12050










