PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
read the original abstract
We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial, temporal, and heterogeneous agent capability constraints. We employ a semi-automated task generation pipeline using Large Language Models (LLMs), incorporating simulation in the loop for grounding and verification. PARTNR stands as the largest benchmark of its kind, comprising 100,000 natural language tasks, spanning 60 houses and 5,819 unique objects. We analyze state-of-the-art LLMs on PARTNR tasks, across the axes of planning, perception and skill execution. The analysis reveals significant limitations in SoTA models, such as poor coordination and failures in task tracking and recovery from errors. When LLMs are paired with real humans, they require 1.5x as many steps as two humans collaborating and 1.1x more steps than a single human, underscoring the potential for improvement in these models. We further show that fine-tuning smaller LLMs with planning data can achieve performance on par with models 9 times larger, while being 8.6x faster at inference. Overall, PARTNR highlights significant challenges facing collaborative embodied agents and aims to drive research in this direction.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
SP-CoR is a multimodal LLM framework using dynamics-aware sampling, spectral-physics view fusion, and prompt distillation that outperforms baselines on the new CoopSR benchmark and EgoTeam dataset for multi-robot coop...
-
PersonalHomeBench: Evaluating Agents in Personalized Smart Homes
PersonalHomeBench is a new benchmark showing that AI agents suffer systematic performance drops in personalized smart homes as task complexity rises, especially in counterfactual reasoning and partial observability.
-
PersonalHomeBench: Evaluating Agents in Personalized Smart Homes
PersonalHomeBench is a new benchmark showing that foundation models struggle with increasing task complexity in personalized smart homes, especially counterfactual reasoning and partial observability.
-
ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs
ST-BiBench reveals a coordination paradox in which MLLMs show strong high-level strategic reasoning yet fail at fine-grained 16-dimensional bimanual action synthesis and multi-stream fusion.
-
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
LLawCo extracts misaligned behavioral patterns from agent failures to derive laws, incorporates them via SFT into LLM reasoning, and reports 4.5% and 6.8% success rate gains on PARTNR-Dialog and TDW-MAT benchmarks.
-
PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration
PACT is an ask-or-act framework using reinforcement learning on interaction history to decide when to seek clarification, improving assistance accuracy and a new clarification utility metric over passive baselines in ...
-
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
EmbodiedGovBench is a new benchmark framework that measures embodied agent systems on seven governance dimensions including policy adherence, recovery success, and upgrade safety.
-
When Should Users Check? Modeling Confirmation Frequency inMulti-Step Agentic AI Tasks
A decision-theoretic model based on the observed Confirmation-Diagnosis-Correction-Redo user pattern places intermediate confirmations in AI agent tasks, yielding 81% user preference and 13.54% faster completion versu...
-
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
TaskGround introduces a Ground-Infer-Execute framework for full-scene household reasoning that improves success rates on the FullHome benchmark and enables compact models to match larger ones at up to 18x lower token cost.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.