ArticleNature machine intelligence2025
Embodied large language models enable robots to complete complex tasks in unpredictable environments.
Article in Nature machine intelligence, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 15 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
15 citing papers in PubMed.
- Surgeon-authorized natural-language and instrument-tracking shared control for robotic laparoscope holding: the EndoVISTA simulator and porcine feasibility study.Journal of robotic surgery · 2026Article
- Large Language Models in Sensor-Driven Control Systems: Architectures, Challenges, and Opportunities.Sensors (Basel, Switzerland) · 2026Review
- How can reasoning capability empower the AI copilot robot in endoscopic surgery.NPJ digital medicine · 2026Article
- Proactive collaboration via autonomous interaction.Nature communications · 2026Article
- WaterRAG: A Multiagent Retrieval-Augmented Generation Framework to Support Water Industry Transitions to Net-Zero.Environmental science & technology · 2026Article
- Attention-based graph neural network framework for non-invasive CAP score prediction in fatty liver disease via body modeling.Physical and engineering sciences in medicine · 2026Article
- PFEA: a VLM-based high-level natural language planning and feedback embodied agent for human-centered AI.Frontiers in robotics and AI · 2026Article
- Convergence of need technology and culture driving the era of physical AI in medicine.Frontiers in digital health · 2026Article
- ISEED: an always-on cognitive architecture for experience-driven interaction-oriented humanoid robots.Frontiers in neurorobotics · 2026Article
- Cross-Modality Alignment Perception and Multi-Head Self-Attention Mechanism for Vision-Language-Action of Humanoid Robot.Sensors (Basel, Switzerland) · 2025Article
- MechRAG: a multimodal large language model for mechanical engineering.Communications engineering · 2025Article
- Big Data and AI-Powered Modeling: A Pathway to Sustainable Precision Animal Nutrition.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Review
- Hinst: Human-Like Interactive Instinct Enables Robots to Robustly Accomplish Universal Tasks.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2025Article
- An AI Agent for cell-type specific brain computer interfaces.bioRxiv : the preprint server for biology · 2025Article
- Orchestrating Embodied Systems through the Embodied Context Protocol: Motivation, Progress, and Directions.Research (Washington, D.C.) · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Completing complex tasks in unpredictable settings challenges robotic systems, requiring a step change in machine intelligence. Sensorimotor abilities are considered integral to human intelligence. Thus, biologically inspired machine intelligence might usefully combine artificial intelligence with robotic sensorimotor capabilities. Here we report an embodied large-language-model-enabled robot (ELLMER) framework, utilizing GPT-4 and a retrieval-augmented generation infrastructure, to enable robots to complete long-horizon tasks in unpredictable settings. The method extracts contextually relevant examples from a knowledge base, producing action plans that incorporate force and visual feedback and enabling adaptation to changing conditions. We tested ELLMER on a robot tasked with coffee making and plate decoration; these tasks consist of a sequence of sub-tasks from drawer opening to pouring, each benefiting from distinct feedback types and methods. We show that the ELLMER framework allows the robot to complete the tasks. This demonstration marks progress towards scalable, efficient and 'intelligent robots' able to complete complex tasks in uncertain environments.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.