cs.ROOct 29, 2026

EmbodiExp: Compositional Experience Transfer for Embodied Agents

Authors: Zhifeng Gu, Ying Chen, Rui Jiang, Lei Yi, Bing Wang

Organizations: Spatial Intelligence Group, The Hong Kong Polytechnic University · XPENG Robotics

Abstract

Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the current state or fail to produce their intended outcomes. We present EmbodiExp, a framework for constructing transferable experiences and composing them online during embodied task execution. Our key observation is that tasks often share subgoals whose completion can be assessed independently of overall task success. We therefore introduce an outcome-grounded subgoal experience that specifies a subgoal, applicability conditions, an adaptable policy, and a verifiable outcome. During execution, applicable experiences guide action generation, while verified outcomes can establish the conditions required by subsequent experiences, enabling online composition. Subgoal-level outcome attribution further enables failure utilization: failed trajectories can still contribute verified local successes and condition-specific guidance on actions to avoid. Experiments on multiple embodied benchmarks under a fold-based protocol with frozen experience banks demonstrate the effectiveness of EmbodiExp.

Explore similar work

CardsList
  1. EMHO: EMbodied Agent Harness Optimization via Experience Traces

    Oct 6, 2026Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong +3Agent Harness OptimizationEmbodied AI

  2. OmniBrain-0: A Unified Agentic Model for Embodied Intelligence

    Oct 26, 2026Xiaomi Embodied Intelligence Team, Yuechen Luo, Chong He +29Embodied AIAgentic AI for Robotics

  3. MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling

    Oct 15, 2026Renhao Li, Xinjie Shen, Yang Su +4LLM Agent Self-ImprovementLLM Agents