EFLUX: Elastic Multi-Robot Formation Navigation and Adaptation with Agentic LLMs

• URL: http://arxiv.org/abs/2607.12050v1
• Date: Mon, 13 Jul 2026 18:08:57 GMT
• Title: EFLUX: Elastic Multi-Robot Formation Navigation and Adaptation with Agentic LLMs
• Abstract summary: Multi-robot teams operating in confined or cluttered environments must adapt both their formation geometry and group topology to navigate through complex obstacles.<n>Existing methods often model these behaviors independently, connect them through handcrafted rules, or lack explicit geometric criteria for determining when each behavior should be invoked.<n>We propose a geometry-grounded LLM agentic framework for automatic and elastic multi-robot formation navigation.
• Score: 24.382645393013945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-robot teams operating in confined or cluttered environments must adapt both their formation geometry and group topology to navigate through complex obstacles. This adaptation requires two complementary behaviors: deformation, where the team continuously reshapes its geometry while remaining connected, and reconfiguration, where robots split into subgroups or merge back into a single formation. Existing methods often model these behaviors independently, connect them through handcrafted rules, or lack explicit geometric criteria for determining when each behavior should be invoked. However, challenging environments may require online changes in formation shape, connectivity, and effective team composition, making decoupled or rule-based approaches prone to suboptimal trajectories and deadlock. We propose EFLUX, a 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, such as scaling and shearing, and reconfiguration actions, such as 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 constrained environments, reducing deadlock and navigation failures compared with baselines while maintaining coherent multi-robot coordination.

Related papers

• Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy [79.09714980186278]
  Building persistent embodied agents in unstructured environments requires unified orchestration of heterogeneous tools.<n>We present OmniAct, a framework integrating a multimodal semantic planner for skill routing across unified action spaces.<n>It achieves consistent improvements in end-to-end success across all complexity levels.
  arXiv  Detail & Related papers  (2026-06-25T16:36:35Z)
• REACT: Environment-Adaptive Architecture for Continuous Formation Navigation of Wheeled Mobile Robots [21.3981924226061]
  We propose REACT, a hierarchical architecture integrating centralized formation generation and distributed formation maintenance.<n>Specifically, our upper layer generates new environment-adaptive formations when necessary.<n>At the lower layer, each WMR executes our developed JSTP (Joint trajectory trajectory Planning) method to maintain the generated formation.
  arXiv  Detail & Related papers  (2026-05-18T14:11:31Z)
• DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training [21.939190885925754]
  We present DynaTrain, a distributed training system for sub-second reconfiguration online across arbitrary multi-dimensional parallelism.<n>At its core, we propose a Virtual VPS Space abstraction that unifies all distributed training states under one logical coordinate space.<n>On dense and MoE models up to 235B parameters, DynaTrains a 70B dense model in under 2s and a 235B MoE model in 4.36s, outperforming state-of-the-art checkpoint-based and elastic systems by up to three orders of magnitude while preserving correctness.
  arXiv  Detail & Related papers  (2026-05-12T09:51:28Z)
• Role-Adaptive Collaborative Formation Planning for Team of Quadruped Robots in Cluttered Environments [15.679419362625845]
  This paper presents a role-adaptive Leader-Follower-based formation planning and control framework for quadruped robots.<n>Unlike conventional methods with fixed leaders or rigid formation roles, the proposed approach integrates dynamic role assignment and partial goal planning.<n>Results demonstrate smooth coordination, switching adaptive role, and robust formation maintenance in complex, unstructured environments.
  arXiv  Detail & Related papers  (2026-02-20T14:44:16Z)
• ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas [13.919124676472022]
  ASTRA is an end-to-end framework for training tool-augmented language model agents.<n>ASTRA integrates scalable data synthesis and verifiable reinforcement learning.<n> Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-01-29T11:22:23Z)
• StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval [75.28673512571449]
  A key challenge in Continual Text-to-Video Retrieval is feature drift.<n>We propose StructAlign, a structured cross-modal alignment method for CTVR.<n>Our method consistently outperforms state-of-the-art continual retrieval approaches.
  arXiv  Detail & Related papers  (2026-01-28T13:34:44Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• Learning to Coordinate: Distributed Meta-Trajectory Optimization Via Differentiable ADMM-DDP [4.880846795915428]
  We propose Learning to Coordinate (L2C) to adapt across diverse tasks and agent configurations.<n>L2C differentiates end-to-end through the ADMM-DDP pipeline in a distributed manner.<n>It achieves up to $88%$ faster gradient computation than state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-01T17:17:05Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.