A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment

• URL: http://arxiv.org/abs/2410.23242v1
• Date: Wed, 30 Oct 2024 17:28:28 GMT
• Title: A little less conversation, a little more action, please: Investigating the physical common-sense of LLMs in a 3D embodied environment
• Authors: Matteo G. Mecattaf, Ben Slater, Marko Tešić, Jonathan Prunty, Konstantinos Voudouris, Lucy G. Cheke,
• Abstract summary: Large Language Models (LLMs) are increasingly used as reasoning engines in agentic systems. We present the first embodied and cognitively meaningful evaluation of physical common-sense reasoning in LLMs. We employ the Animal-AI environment, a simulated 3D virtual laboratory, to study physical common-sense reasoning in LLMs.
• Score: 0.9188951403098383
• License:
• Abstract: As general-purpose tools, Large Language Models (LLMs) must often reason about everyday physical environments. In a question-and-answer capacity, understanding the interactions of physical objects may be necessary to give appropriate responses. Moreover, LLMs are increasingly used as reasoning engines in agentic systems, designing and controlling their action sequences. The vast majority of research has tackled this issue using static benchmarks, comprised of text or image-based questions about the physical world. However, these benchmarks do not capture the complexity and nuance of real-life physical processes. Here we advocate for a second, relatively unexplored, approach: 'embodying' the LLMs by granting them control of an agent within a 3D environment. We present the first embodied and cognitively meaningful evaluation of physical common-sense reasoning in LLMs. Our framework allows direct comparison of LLMs with other embodied agents, such as those based on Deep Reinforcement Learning, and human and non-human animals. We employ the Animal-AI (AAI) environment, a simulated 3D virtual laboratory, to study physical common-sense reasoning in LLMs. For this, we use the AAI Testbed, a suite of experiments that replicate laboratory studies with non-human animals, to study physical reasoning capabilities including distance estimation, tracking out-of-sight objects, and tool use. We demonstrate that state-of-the-art multi-modal models with no finetuning can complete this style of task, allowing meaningful comparison to the entrants of the 2019 Animal-AI Olympics competition and to human children. Our results show that LLMs are currently outperformed by human children on these tasks. We argue that this approach allows the study of physical reasoning using ecologically valid experiments drawn directly from cognitive science, improving the predictability and reliability of LLMs.

Related papers

• Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina [7.155982875107922]
  Studies suggest large language models (LLMs) can exhibit human-like reasoning, aligning with human behavior in economic experiments, surveys, and political discourse. This has led many to propose that LLMs can be used as surrogates for humans in social science research. We assess the reasoning depth of LLMs using the 11-20 money request game.
  arXiv  Detail & Related papers  (2024-10-25T14:46:07Z)
• Cognitive phantoms in LLMs through the lens of latent variables [0.3441021278275805]
  Large language models (LLMs) increasingly reach real-world applications, necessitating a better understanding of their behaviour. Recent studies administering psychometric questionnaires to LLMs report human-like traits in LLMs, potentially influencing behaviour. This approach suffers from a validity problem: it presupposes that these traits exist in LLMs and that they are measurable with tools designed for humans. This study investigates this problem by comparing latent structures of personality between humans and three LLMs using two validated personality questionnaires.
  arXiv  Detail & Related papers  (2024-09-06T12:42:35Z)
• WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks [85.95607119635102]
  Large language models (LLMs) can mimic human-like intelligence. WorkArena++ is designed to evaluate the planning, problem-solving, logical/arithmetic reasoning, retrieval, and contextual understanding abilities of web agents.
  arXiv  Detail & Related papers  (2024-07-07T07:15:49Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs [62.496139001509114]
  We introduce a novel tool invocation pipeline designed to control massive real-world APIs. This pipeline mirrors the human task-solving process, addressing complicated real-life user queries. Empirical evaluations of our Sum2Act pipeline on the ToolBench benchmark show significant performance improvements.
  arXiv  Detail & Related papers  (2024-02-28T08:42:23Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• LLM-driven Imitation of Subrational Behavior : Illusion or Reality? [3.2365468114603937]
  Existing work highlights the ability of Large Language Models to address complex reasoning tasks and mimic human communication. We propose to investigate the use of LLMs to generate synthetic human demonstrations, which are then used to learn subrational agent policies. We experimentally evaluate the ability of our framework to model sub-rationality through four simple scenarios.
  arXiv  Detail & Related papers  (2024-02-13T19:46:39Z)
• Limits of Large Language Models in Debating Humans [0.0]
  Large Language Models (LLMs) have shown remarkable promise in their ability to interact proficiently with humans. This paper endeavors to test the limits of current-day LLMs with a pre-registered study integrating real people with LLM agents acting as people.
  arXiv  Detail & Related papers  (2024-02-06T03:24:27Z)
• SimLM: Can Language Models Infer Parameters of Physical Systems? [56.38608628187024]
  We investigate the performance of Large Language Models (LLMs) at performing parameter inference in the context of physical systems. Our experiments suggest that they are not inherently suited to this task, even for simple systems. We propose a promising direction of exploration, which involves the use of physical simulators to augment the context of LLMs.
  arXiv  Detail & Related papers  (2023-12-21T12:05:19Z)
• LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark [81.42376626294812]
  We present Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark. Our aim is to establish LAMM as a growing ecosystem for training and evaluating MLLMs. We present a comprehensive dataset and benchmark, which cover a wide range of vision tasks for 2D and 3D vision.
  arXiv  Detail & Related papers  (2023-06-11T14:01:17Z)
• Are LLMs the Master of All Trades? : Exploring Domain-Agnostic Reasoning Skills of LLMs [0.0]
  This study aims to investigate the performance of large language models (LLMs) on different reasoning tasks. My findings indicate that LLMs excel at analogical and moral reasoning, yet struggle to perform as proficiently on spatial reasoning tasks.
  arXiv  Detail & Related papers  (2023-03-22T22:53:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.