LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging

• URL: http://arxiv.org/abs/2605.01461v1
• Date: Sat, 02 May 2026 14:21:26 GMT
• Title: LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging
• Abstract summary: LLM-Foraging is a decentralized swarm controller that augments the CPFA state machine with a large language model (LLM) tactical decision-maker.<n>Each robot runs its own LLM client and queries it using only locally observable state, while the existing CPFA motion and sensing stack executes the selected action.<n>We evaluate LLM-Foraging in Gazebo with TurtleBot3 robots across 36 configurations spanning team sizes of 4 to 10 robots, arena sizes from 6x6 to 10x10 meters, and three resource distributions.
• Score: 13.56144018976383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Swarm foraging algorithms, such as the central-place foraging algorithm (CPFA), typically rely on offline parameter optimization using genetic algorithms (GA) or reinforcement learning, yielding policies tightly coupled to a specific combination of team size, arena size, and resource distribution. When deployment conditions change, performance degrades, and retraining is computationally expensive. We propose LLM-Foraging, a decentralized swarm controller that augments the CPFA state machine with a large language model (LLM) tactical decision-maker at three structured decision points, namely post-deposit, central-zone arrival, and search starvation. Each robot runs its own LLM client and queries it using only locally observable state, while the existing CPFA motion and sensing stack executes the selected action. Because the LLM serves as a general decision policy rather than parameters fitted to a single configuration, the controller is training-free at deployment and transfers across configurations without re-optimization. We evaluate LLM-Foraging in Gazebo with TurtleBot3 robots across 36 configurations spanning team sizes of 4 to 10 robots, arena sizes from 6x6 to 10x10 meters, and three resource distributions (clustered, powerlaw, random). LLM-Foraging collects more resources than the GA-tuned CPFA baseline across the evaluated configurations and is more consistent, a property that the GA's single-configuration tuning does not transfer.

Related papers

• A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning [0.0]
  Three robots share motion dynamics but use different LLM backends.<n>Each robot independently combines a large language model (LLM) policy agent, an Upper Confidence Bound (UCB) bandit, and a Double Deep Q-Network (Double DQN) controller.<n>The robots perform cross-LLM communication through a shared round summary containing policies, outcomes, and learning feedback.
  arXiv  Detail & Related papers  (2026-09-04T13:35:55Z)
• Unifying Local Communications and Local Updates for LLM Pretraining [22.321729036377846]
  Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters.<n>We introduce GASLoC, a novel decentralized pre-training algorithm that generalizes the notion of communication acceleration to allow a practical gossip-based training framework.<n>We demonstrate that GASLoC outperforms state-of-the-art decentralized algorithms in single step per communication setting for a number of topologies.
  arXiv  Detail & Related papers  (2026-06-09T16:40:54Z)
• 3SPO: State-Score-Supervised Policy Optimization for LLM Agents [25.01222941080024]
  We propose textbfState-Score-Supervised Policy Optimization (3SPO), a novel RL algorithm that performs post-step policy optimization with dynamic state score supervision.<n> Experiments on ALFWorld and WebShop with Qwen2.5-1.5B/7B-Instruct show that 3SPO consistently outperforms GRPO by $+22.6%$ on ALFWorld and $+15.6$ points on WebShop.
  arXiv  Detail & Related papers  (2026-06-08T14:26:05Z)
• AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control [4.365822392824561]
  AutoSiMP transforms a natural-language structural problem description into a validated, binary topology without manual configuration.<n>The pipeline comprises five modules: (1) an LLM-based solver that parses a plain-English prompt into a validated specification of geometry, supports, loads, passive regions, and mesh parameters; (2) a boundary-condition generator producing solver-ready DOF arrays, force vectors, and passive-element masks; and (3) a three-field SIMP solver with Heaviside projection and pluggable continuation control.
  arXiv  Detail & Related papers  (2026-03-27T21:23:44Z)
• ChunkWise LoRA: Adaptive Sequence Partitioning for Memory-Efficient Low-Rank Adaptation and Accelerated LLM Inference [0.21064685964744576]
  ChunkWise LoRA partitions sequences into variable-length chunks based on token complexity and assigns each chunk a tailored low-rank configuration.<n>Experiments on benchmark datasets such as Wikitext-103 and SQuAD demonstrate that ChunkWise LoRA achieves up to 34% lower latency and 38% memory reduction.
  arXiv  Detail & Related papers  (2026-01-28T22:58:28Z)
• RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure [49.88201789074532]
  Agentic Reinforcement Learning (RL) enables Large Language Models (LLMs) to perform autonomous decision-making and long-term planning.<n>We present RollArc, a distributed system designed to maximize throughput for multi-task agentic RL on disaggregated infrastructure.
  arXiv  Detail & Related papers  (2025-12-27T11:14:23Z)
• RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory [57.449129198822476]
  RCR is a role-aware context routing framework for multi-agent large language model (LLM) systems.<n>It dynamically selects semantically relevant memory subsets for each agent based on its role and task stage.<n>A lightweight scoring policy guides memory selection, and agent outputs are integrated into a shared memory store.
  arXiv  Detail & Related papers  (2025-08-06T21:59:34Z)
• PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning [54.99373314906667]
  Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks.<n>As pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources.<n>We propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models.
  arXiv  Detail & Related papers  (2025-04-22T16:41:21Z)
• AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs [68.99086112477565]
  Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation.<n>Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads.<n>We propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single- GPU and multi- GPU environments.
  arXiv  Detail & Related papers  (2025-02-27T14:46:22Z)
• Decentralized Low-Rank Fine-Tuning of Large Language Models [12.270878920401948]
  We propose Dec-LoRA, a decentralized fine-tuning algorithm for Large Language Models (LLMs) based Low-Rank Adaptation (LoRA)<n>Through experiments on BERT and LLaMA, we demonstrate that Dec-LoRA achieves comparable performance to centralized LoRA under various conditions.<n>These findings highlight the potential of Dec-LoRA for scalable fine-tuning in decentralized environments.
  arXiv  Detail & Related papers  (2025-01-26T01:56:25Z)
• A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation [4.144893164317513]
  We introduce a novel framework using a decentralized partially observable Markov decision process (Dec_POMDP)<n>At the core of our methodology is the Local Information Aggregation Multi-Agent Deep Deterministic Policy Gradient (LIA_MADDPG) algorithm.<n>Our empirical evaluations show that the LIA module can be seamlessly integrated into various CTDE-based MARL methods.
  arXiv  Detail & Related papers  (2024-11-29T07:53:05Z)
• Octo-planner: On-device Language Model for Planner-Action Agents [19.627197141903505]
  Planner-Action framework separates planning and action execution into two distinct components. Agent first responds to user queries by decomposing tasks into a sequence of sub-steps, which are then executed by the action agent. We employ model fine-tuning instead of in-context learning, reducing computational costs and energy consumption.
  arXiv  Detail & Related papers  (2024-06-26T05:40:10Z)
• Distributed Inference and Fine-tuning of Large Language Models Over The Internet [91.00270820533272]
  Large language models (LLMs) are useful in many NLP tasks and become more capable with size. These models require high-end hardware, making them inaccessible to most researchers. We develop fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput.
  arXiv  Detail & Related papers  (2023-12-13T18:52:49Z)
• Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes [53.4856038354195]
  Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions. FedKSeed employs zeroth-order optimization with a finite set of random seeds. It significantly reduces transmission requirements between the server and clients to just a few random seeds.
  arXiv  Detail & Related papers  (2023-12-11T13:03:21Z)

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.