REVIEW 6 cited by
LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Language models (LMs) possess a strong capability to comprehend natural language, making them effective in translating human instructions into detailed plans for simple robot tasks. Nevertheless, it remains a significant challenge to handle long-horizon tasks, especially in subtask identification and allocation for cooperative heterogeneous robot teams. To address this issue, we propose a Language Model-Driven Multi-Agent PDDL Planner (LaMMA-P), a novel multi-agent task planning framework that achieves state-of-the-art performance on long-horizon tasks. LaMMA-P integrates the strengths of the LMs' reasoning capability and the traditional heuristic search planner to achieve a high success rate and efficiency while demonstrating strong generalization across tasks. Additionally, we create MAT-THOR, a comprehensive benchmark that features household tasks with two different levels of complexity based on the AI2-THOR environment. The experimental results demonstrate that LaMMA-P achieves a 105% higher success rate and 36% higher efficiency than existing LM-based multiagent planners. The experimental videos, code, datasets, and detailed prompts used in each module can be found on the project website: https://lamma-p.github.io.
Forward citations
Cited by 6 Pith papers
-
RoboReact: Agentic Skill Distillation from Generated Egocentric Videos for Generalizable Whole-Body Manipulation
From a single egocentric RGB-D frame and a language instruction, RoboReact generates a human manipulation video, distills it into object-relative keyframe skills, refines them through a vision-language-model trial loo...
-
A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation
A closed-loop multi-agent LLM framework enables heterogeneous robots to collaboratively manipulate objects by decomposing tasks, grounding actions via visual tools, and recovering from execution failures hierarchically.
-
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
A three-level temporal-logic safety evaluator for embodied LLM agents that checks NL-to-LTL interpretation, plan compliance, and CTL over simulated execution trees.
-
CollaBot: Vision-Language Guided Simultaneous Collaborative Manipulation
Vision-language guided multi-robot large-object manipulation, reported at 52 percent simulation success in the body text but advertised as 72 percent in the metadata abstract, with no baseline comparison.
-
Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning
TAPAS uses several specialized language-model agents to generate, correct, and adapt symbolic planning problems, reporting high benchmark accuracy and a virtual-home execution demo.
-
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization
Pseudocode-structured plans paired with preference optimization improve LLM agent success rates and generalization across interactive benchmarks.
Discussion (0). Continue with ORCID to comment.