跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26196 · v1

EmbodyAgent: Post-Training Embodied VLM Agents via Distillation, SFT, and RL

首次提交 2026-11-19 22:41
版本更新 2026-11-19 22:41
雷达观测 2026-11-20 14:52
arXiv ↗PDF ↗

摘要

Vision-language models (VLMs) can act as closed-loop robot-use agents (RUAs) by writing and executing control code through tool interfaces. However, turning an open-weight VLM into a high-performing embodied agent requires a complete post-training stack: out-of-the-box open VLMs fail completely at interactive tool contracts, strong frontier teachers are accessible only as black-box endpoints without exposed weights or token probabilities, and supervised imitation alone plateaus under rollout distribution shift. We present EmbodyAgent, an end-to-end post-training framework with three tightly coupled pipelines: (1) a black-box data synthesis pipeline that queries a strong teacher under a forced think-then-code contract and filters trajectories by task success; (2) an SFT pipeline that distills the explanation-and-program targets into an open-weight 9B VLM with both vision and language encoders trainable; and (3) an online RL pipeline that optimizes student-generated episodes via group-relative advantage with a runtime-error-penalized outcome reward. All three pipelines share one primitive-free Python execution tool exposing only raw visual observation and seven-dimensional end-effector control, with no action decoder and no interface shift across stages. Under a strictly separated evaluation protocol on ten LIBERO Spatial tasks (disjoint state splits, greedy test-time decoding, training-only safeguards), held-out success on 100 test states rises from 0/100 (base 9B VLM) to 14/100 (after SFT) and 84/100 (after RL), while training rollout success climbs from 8.4% to 87.7% and median model calls per episode drop from 36 to 11. We further identify a self-reinforcing runtime-error mode induced by outcome-based RL on executable code, and establish a failure-category monitoring and sampling-side curation protocol that stabilizes training.

作者备注:11 pages, 4 figures. Code-as-policy robot-use agent post-training

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-19 22:41 · 最新观测版本

EmbodyAgent: Post-Training Embodied VLM Agents via Distillation, SFT, and RL

Vision-language models (VLMs) can act as closed-loop robot-use agents (RUAs) by writing and executing control code through tool interfaces. However, turning an open-weight VLM into a high-performing embodied agent requires a complete post-training stack: out-of-the-box open VLMs fail completely at interactive tool contracts, strong frontier teachers are accessible only as black-box endpoints without exposed weights or token probabilities, and supervised imitation alone plateaus under rollout distribution shift. We present EmbodyAgent, an end-to-end post-training framework with three tightly coupled pipelines: (1) a black-box data synthesis pipeline that queries a strong teacher under a forced think-then-code contract and filters trajectories by task success; (2) an SFT pipeline that distills the explanation-and-program targets into an open-weight 9B VLM with both vision and language encoders trainable; and (3) an online RL pipeline that optimizes student-generated episodes via group-relative advantage with a runtime-error-penalized outcome reward. All three pipelines share one primitive-free Python execution tool exposing only raw visual observation and seven-dimensional end-effector control, with no action decoder and no interface shift across stages. Under a strictly separated evaluation protocol on ten LIBERO Spatial tasks (disjoint state splits, greedy test-time decoding, training-only safeguards), held-out success on 100 test states rises from 0/100 (base 9B VLM) to 14/100 (after SFT) and 84/100 (after RL), while training rollout success climbs from 8.4% to 87.7% and median model calls per episode drop from 36 to 11. We further identify a self-reinforcing runtime-error mode induced by outcome-based RL on executable code, and establish a failure-category monitoring and sampling-side curation protocol that stabilizes training.

查看此版本解读 →查看此版本原文 ↗