A scalable communication protocol for networks of large language models

S Marro, E La Malfa, J Wright, G Li, N Shadbolt… - arXiv preprint arXiv …, 2024 - arxiv.org
Communication is a prerequisite for collaboration. When scaling networks of AI-powered
agents, communication must be versatile, efficient, and portable. These requisites, which we …

ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation

A Anwar, J Welsh, J Biswas, S Pouya… - arXiv preprint arXiv …, 2024 - arxiv.org
Navigating and understanding complex environments over extended periods of time is a
significant challenge for robots. People interacting with the robot may want to ask questions …

Bootstrapping Object-level Planning with Large Language Models

D Paulius, A Agostini, B Quartey… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce a new method that extracts knowledge from a large language model (LLM) to
produce object-level plans, which describe high-level changes to object state, and uses …

Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments

S Nayak, AM Orozco, MT Have, V Thirumalai… - arXiv preprint arXiv …, 2024 - arxiv.org
The ability of Language Models (LMs) to understand natural language makes them a
powerful tool for parsing human instructions into task plans for autonomous robots. Unlike …

DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning

Z Gao, Y Mu, J Qu, M Hu, L Guo, P Luo, Y Lu - arXiv preprint arXiv …, 2024 - arxiv.org
Dual-arm robots offer enhanced versatility and efficiency over single-arm counterparts by
enabling concurrent manipulation of multiple objects or cooperative execution of tasks using …

SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

R Yang, J Chen, Y Zhang, S Yuan, A Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Language agents powered by large language models (LLMs) are increasingly valuable as
decision-making tools in domains such as gaming and programming. However, these …

Evaluating Creativity and Deception in Large Language Models: A Simulation Framework for Multi-Agent Balderdash

P Hejabi, E Rahmati, AS Ziabari, P Golazizian… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have shown impressive capabilities in complex tasks and
interactive environments, yet their creativity remains underexplored. This paper introduces a …

Hierarchical LLMs In-the-loop Optimization for Real-time Multi-Robot Target Tracking under Unknown Hazards

Y Wu, Y Tao, P Li, G Shi, GS Sukhatmem… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we propose a hierarchical Large Language Models (LLMs) in-the-loop
optimization framework for real-time multi-robot task allocation and target tracking in an …

LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner

X Zhang, H Qin, F Wang, Y Dong, J Li - arXiv preprint arXiv:2409.20560, 2024 - arxiv.org
Language models (LMs) possess a strong capability to comprehend natural language,
making them effective in translating human instructions into detailed plans for simple robot …

MAP-THOR: Benchmarking Long-Horizon Multi-Agent Planning Frameworks in Partially Observable Environments

S Nayak, AM Orozco, M Ten Have, V Thirumalai… - Multi-modal Foundation … - openreview.net
Evaluating embodied multi-agent planners necessitates robust and versatile benchmarks.
We introduce MAP-THOR (Multi-Agent Planning in AI2-THOR), a benchmark specifically …