Pub-AI: AI in Science

Latent Dynamics · 2026-09-30

In-Context Learning for Robots: Methods and Applications

Haojian Huang, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xinyi Li, Runze Li, Peiran Dong, Shaoxiang Dang, Jing Huang, Yingbing Chen, Yifan Chang, Tianyi Zhang, Shiyuan Deng, Haozhi Wang, Yangkai Wei, Wenqian Li, Han Yang, Kaiwen Zhou, Huaping Liu, James Cheng, Rui Shao, Donglin Wang, Yaochu Jin, Jianye Hao, Ying-Cong Chen, Yinchuan Li

arXiv:2609.36012PDF

Auto-summarized: this summary was generated by a language model from the paper’s text and has not been reviewed by an editor. Check the paper before relying on it. Benchmark numbers appear only after a human has verified them.

TL;DR

The authors review in-context learning (ICL) for robots, where demonstrations and interaction change deployed behavior without updating neural parameters during deployment. They organize prior work into four interfaces connecting context to execution: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution, analyzing how training, correspondence, and memory determine whether taught requirements transfer under changing objects, environments, and execution conditions.

Why it matters

For general-purpose robots, the key challenge is inferring what a new task requires from evidence and executing it with existing competence. By comparing four context-to-execution interfaces and focusing on how training relationships and memory/correspondence affect context validity, the survey links method design to evaluations that separate responsiveness to teaching, physical transfer, and benefits from retained experience.

Method

  • Organize robot ICL literature by interfaces connecting contextual evidence to execution: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution.
  • Explain how transfer depends on training relationships, and on mechanisms (correspondence, training, and memory) that preserve needed information across changing objects, environments, and execution conditions.
  • Connect method design to evaluation practices distinguishing context dependence, physical transfer, responsiveness to teaching, and retained-experience benefits.
Abstract (from arXiv)

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.

Related papers