{"arxiv_id":"2609.34261","title":"RoboICL: Embodied In-Context Learning with GPT-6 Astra","abstract":"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 \\emph{RoboICL}, an in-context robot-control framework that narrows these gaps without robot-specific parameter updates or a learned VLA. RoboICL separates \\emph{demonstration context}, which provides recorded examples when available, from \\emph{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 $\\pi_{0.5}$ + \\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 \\href{https://github.com/Mosi-AI/RoboICL}{https://github.com/Mosi-AI/RoboICL}.","primary_cat":"cs.RO","cross_cats":["cs.LG"],"submitted_at":"2026-09-28T04:07:36+00:00","latest_version":1,"source":"arxiv","source_label":"arXiv","source_url":null,"has_pdf":true,"has_source":false,"verdict":"CONDITIONAL","confidence":"MODERATE","one_line_summary":"In-context organization of demonstrations and the robot's own rollout history lets a frozen GPT-6 Astra match or beat trained robot policies on RoboDojo precision and long-horizon tasks without parameter updates.","novelty_score":5.0,"correctness_risk":"medium","formal_verification":"none","upvotes":0,"downvotes":0,"pith_score":0.0,"inbound_count":18,"_links":{"html":"https://pith.science/paper/2609.34261","verdict":"/api/v1/verdicts/2609.34261"}}