pith. sign in

arxiv: 2407.10031 · v2 · pith:2AHLR3KUnew · submitted 2024-07-14 · 💻 cs.RO · cs.MA

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

Siddharth Nayak , Adelmo Morrison Orozco , Marina Ten Have , Vittal Thirumalai , Jackson Zhang , Darren Chen , Aditya Kapoor , Eric Robinson
show 5 more authors
Karthik Gopalakrishnan James Harrison Brian Ichter Anuj Mahajan Hamsa Balakrishnan
This is my paper
classification 💻 cs.RO cs.MA
keywords llamartaskslong-horizonmulti-agentobservablepartiallyplanningachieves
0
0 comments X
read the original abstract

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 traditional planning methods that rely on domain-specific knowledge and handcrafted rules, LMs generalize from diverse data and adapt to various tasks with minimal tuning, acting as a compressed knowledge base. However, LMs in their standard form face challenges with long-horizon tasks, particularly in partially observable multi-agent settings. We propose an LM-based Long-Horizon Planner for Multi-Agent Robotics (LLaMAR), a cognitive architecture for planning that achieves state-of-the-art results in long-horizon tasks within partially observable environments. LLaMAR employs a plan-act-correct-verify framework, allowing self-correction from action execution feedback without relying on oracles or simulators. Additionally, we present MAP-THOR, a comprehensive test suite encompassing household tasks of varying complexity within the AI2-THOR environment. Experiments show that LLaMAR achieves a 30% higher success rate than other state-of-the-art LM-based multi-agent planners in MAP-THOR and Search \& Rescue tasks. Code can be found at https://github.com/nsidn98/LLaMAR

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning

    cs.AI 2026-06 unverdicted novelty 7.0

    MultiUAV-Plat supplies a new RESTful simulation platform and 1500-task benchmark where Agent4Drone reaches 57.9% task pass rate versus 30.6% for ReAct baseline across 75 multi-UAV missions.

  2. Closed-Loop Vision-Language Planning for Multi-Agent Coordination

    cs.AI 2025-02 unverdicted novelty 7.0

    COMPASS uses VLMs to generate and refine code-based strategies with structured communication, achieving 57% win rate on SMACv2 Protoss 5v5 versus 27% for QMIX.

  3. PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement

    cs.AI 2026-05 unverdicted novelty 6.0

    PIVOT refines LLM agent trajectories through plan-inspect-evolve-verify stages using environment feedback, yielding up to 94% relative gains in constraint satisfaction and 3-5x token efficiency over prior refinement methods.

  4. Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web

    cs.AI 2026-01 unverdicted novelty 6.0

    Holos is a five-layer LLM-based multi-agent system architecture using the Nuwa engine for agent generation, a market-driven Orchestrator for coordination, and an endogenous value cycle for incentive-compatible persist...

  5. Ask the World Before Acting: Budgeted Environment Probing for World-Model Calibration

    cs.AI 2026-06 unverdicted novelty 4.0

    Introduces budgeted environment probing for structured belief tables in long-horizon agents, with type-stratified analysis showing reduced terminal world-model error when probes follow task structure.