paper-with-me

Papers

ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments

2022-10-01 · COLING 2022 10 · Michael Hanna, Federico Pedeni, Alessandro Suglia, Alberto Testoni, Raffaella Bernardi

Artificial agents are nowadays challenged to perform embodied AI tasks. To succeed, agents must understand the meaning of verbs and how their corresponding actions transform the surrounding world. In this work, we propose ACT-Thor, a novel controlled benchmark for embodied action understanding. We use the AI2-THOR simulated environment to produce a controlled setup in which an agent, given a before-image and an associated action command, has to determine what the correct after-image is among a set of possible candidates. First, we assess the feasibility of the task via a human evaluation that resulted in 81.4% accuracy, and very high inter-annotator agreement (84.9%). Second, we design both unimodal and multimodal baselines, using state-of-the-art visual feature extractors. Our evaluation and error analysis suggest that only models that have a very structured representation of the actions together with powerful visual features can perform well on the task. However, they still fall behind human performance in a zero-shot scenario where the model is exposed to unseen (action, object) pairs. This paves the way for a systematic way of evaluating embodied AI agents that understand grounded actions.

📄 PDF Abstract BibTeX

Code (1)

hannamw/act-thor 공식 구현 pytorch

Tasks

Action Understanding

Similar Papers 제목 키워드 기반

ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

2022-06-14 · Matt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs 외

Massive datasets and high-capacity models have driven many recent advancements in computer vision and natural language understanding. This work presents a platform to enable similar success stories in Embodied AI. We pro…

Natural Language Understanding

Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning

2025-05-22 · Bosung Kim, Prithviraj Ammanabrolu

We introduce $\infty$-THOR, a new framework for long-horizon embodied tasks that advances long-context understanding in embodied AI. $\infty$-THOR provides: (1) a generation framework for synthesizing scalable, reproduci…

Long-Context Understanding

EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models

2024-06-09 · Mengfei Du, Binhao Wu, Zejun Li, Xuanjing Huang 외

The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly …

Benchmarking

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

2026-06-12 · Jixuan Chen, Jianzhi Shen, Haoqiang Kang, Zhi Hong 외 arxiv

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are …

Hy-Embodied-VLM-1.0: Efficient Physical-World Agents

2026-07-14 · Ziyi Wang, Xumin Yu, Yongming Rao, Yonggen Ling 외 arxiv

Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical wo…