ETA: A New Agentic Paradigm for Embodied Tasks

• URL: http://arxiv.org/abs/2608.03924v1
• Date: Tue, 04 Aug 2026 16:56:09 GMT
• Title: ETA: A New Agentic Paradigm for Embodied Tasks
• Abstract summary: We introduce the Embodied Task Agent (ETA), a new paradigm for extending digital agents into the physical world.<n>ETA centers the robot around a Planner that chooses one Tool call at a time, an Interface that controls execution, and a World that returns the result and a fresh observation.<n>ETA provides replaceable Planners, composable Tools and Skills, auditable memory, replayable trajectories, and common interfaces for simulation and real robots.
• Score: 76.25893120982523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When will robots have their ChatGPT moment? Such a breakthrough requires a general-purpose robot that can handle unfamiliar tasks in unfamiliar environments, remain controllable over long interactions, and learn from experience. Today's embodied systems largely follow an end-to-end observation-to-action path. Despite rapid progress, they remain far from this goal: their generalization depends heavily on the coverage of robot training data, while long task execution remains difficult to control and inspect. To realize this goal, we introduce the Embodied Task Agent (ETA), a new paradigm for extending digital agents into the physical world, and release OpenETA as its open-source implementation. ETA centers the robot around a Planner that chooses one Tool call at a time, an Interface that controls execution, and a World that returns the result and a fresh observation. This loop allows the agent to verify outcomes, adapt its plan, and turn successful and failed interactions into reusable experience. OpenETA provides replaceable Planners, composable Tools and Skills, auditable memory, replayable trajectories, and common interfaces for simulation and real robots. For Codex, OpenETA can operate as a lightweight plugin that exposes only observe, mark_point, and move_to.

Related papers

• Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs [6.2312877626161205]
  This paper introduces Physical Agentic AI, a framework for skill-grounded robot agent orchestration.<n>A Robot Orchestration layer exposes the skill library, robot state, named locations, and workflow contracts to a non-actuating Mission Planner.<n>We evaluate on a drone-UGV search-and-dispatch mission, where every mission in every condition is executed live in Gazebo.
  arXiv  Detail & Related papers  (2026-08-23T23:35:31Z)
• A Glimpse into Long-term Physical Coexistence with Intelligent Robots [12.275897522668858]
  PHILIA is a multi-robot agent built around a robot gateway abstraction.<n>It decouples low-frequency, high-semantic agent reasoning from high-frequency, low-level robot execution.<n>We present representative use cases in which agent memory and scene understanding are grounded in robot actions.
  arXiv  Detail & Related papers  (2026-07-13T10:40:32Z)
• VIA: Visual Interface Agent for Robot Control [34.69686658431114]
  VIA (Visual Interface Agent for robot control) is a framework that recasts robot control as an agentic task.<n>It drives a manipulator through a browser-based 3D interface by taking screenshots, issuing intuitive commands, observing the outcome, and adjusting.<n>It achieves 96.7% success on three LIBERO-Goal tasks and 100% on a long-horizon rainbow assembly task.
  arXiv  Detail & Related papers  (2026-07-13T05:52:12Z)
• VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation [32.23131310342716]
  Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes.<n>We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools.<n>We propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout.
  arXiv  Detail & Related papers  (2026-06-05T16:21:27Z)
• NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning [36.20611975009607]
  We introduce NovaPlan, a hierarchical framework that unifies closed-loop VLM and video planning.<n>At the high level, a VLM planner decomposes tasks into sub-goals and monitors robot execution in a closed loop.<n>To compute low-level robot actions, we extract and utilize both task-relevant object keypoints and human hand poses.
  arXiv  Detail & Related papers  (2026-02-23T18:35:18Z)
• COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models [49.24666980374751]
  COHERENT is a novel LLM-based task planning framework for collaboration of heterogeneous multi-robot systems.<n>A Proposal-Execution-Feedback-Adjustment mechanism is designed to decompose and assign actions for individual robots.<n>The experimental results show that our work surpasses the previous methods by a large margin in terms of success rate and execution efficiency.
  arXiv  Detail & Related papers  (2024-09-23T15:53:41Z)
• Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models [53.22792173053473]
  We introduce an interactive robotic manipulation framework called Polaris. Polaris integrates perception and interaction by utilizing GPT-4 alongside grounded vision models. We propose a novel Synthetic-to-Real (Syn2Real) pose estimation pipeline.
  arXiv  Detail & Related papers  (2024-08-15T06:40:38Z)
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
  We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation. Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal. We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
  arXiv  Detail & Related papers  (2024-05-02T17:56:55Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• ALAN: Autonomously Exploring Robotic Agents in the Real World [28.65531878636441]
  ALAN is an autonomously exploring robotic agent that can perform tasks in the real world with little training and interaction time. This is enabled by measuring environment change, which reflects object movement and ignores changes in the robot position. We evaluate our approach on two different real-world play kitchen settings, enabling a robot to efficiently explore and discover manipulation skills.
  arXiv  Detail & Related papers  (2023-02-13T18:59:09Z)
• Projection Mapping Implementation: Enabling Direct Externalization of Perception Results and Action Intent to Improve Robot Explainability [62.03014078810652]
  Existing research on non-verbal cues, e.g., eye gaze or arm movement, may not accurately present a robot's internal states. Projecting the states directly onto a robot's operating environment has the advantages of being direct, accurate, and more salient.
  arXiv  Detail & Related papers  (2020-10-05T18:16:20Z)

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.