# RoboICL: Embodied In-Context Learning with GPT-6 Astra

arXiv: https://arxiv.org/abs/2609.34261 · HTML: https://mlsanity.com/paper/2609.34261/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies](https://mlsanity.com/paper/2607.04434/) (2026)
- [Instant Policy: In-Context Imitation Learning via Graph Diffusion](https://mlsanity.com/paper/2411.12633/) (2024)
- [In-Context Learning Enables Robot Action Prediction in LLMs](https://mlsanity.com/paper/2410.12782/) (2024)
- [RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models](https://mlsanity.com/paper/2508.02062/) (2025)
- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [G0.5: One Autoregressive Stream for Robot Reasoning and Action](https://mlsanity.com/paper/2608.11739/) (2026)
- [Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization](https://mlsanity.com/paper/2608.26103/) (2026)
- [An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond](https://mlsanity.com/paper/2609.24170/) (2026)
- [In-Context Robot Learning with VLM Agents](https://mlsanity.com/paper/2609.19138/) (2026)
- [Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation](https://mlsanity.com/paper/2608.30880/) (2026)
- [Reflective VLA: In-Context Action Consequences Make VLAs Generalize](https://mlsanity.com/paper/2606.25215/) (2026)

## Abstract (arXiv)

General-purpose vision-language models offer a promising way to zero-shot robot control: gptastra excels at open-ended and language- or image-conditioned manipulation but remains substantially weaker on high-precision and long-horizon tasks. We introduce RoboICL, an in-context robot-control framework that narrows these gaps without robot-specific parameter updates or a learned VLA. RoboICL separates demonstration context, which provides recorded examples when available, from interaction memory, which accumulates the model's own actions and observed outcomes. Both use a shared observation--action--receipt--observation grammar. To preserve experience across task stages, RoboICL combines sampled demonstration blocks with bounded anchored memory. Fixed anchors keep earlier rollout interactions available for in-context learning, while the latest interaction supports immediate error correction. Across 30 RoboDojo tasks, using zero shot for Open and one demonstration elsewhere, RoboICL improves on official zero-shot gptastra by 20--27 progress-score points in every category. It leads the leaderboard baselines on Memory and Open, achieves comparable performance to the strongest Precision baseline, and remains competitive on Long-Horizon. Its 30-task Overall score is 50.64, versus 33.68 for the strongest baseline. On a separate ten-task subset, RoboICL scores 60.60, within 2.00 points of the π0.5 + gptastra hybrid approach. On three real-robot tasks, mean progress rises from 14.45 at zero shot to 63.33 at one shot and 78.89 at three shots. On two development tasks, optional Jev-gated action reuse reduces gptastra calls by 33--48%. Code is available at hrefhttps://github.com/Mosi-AI/RoboICLhttps://github.com/Mosi-AI/RoboICL.