---
title: "Cortex：一种双向对齐的具身智能体框架，实现长程操作"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.05377v1"
permalink: "https://feed.astralor.com/items/itm_7a3ae66350397ad980c4d73c"
published: "2026-07-06T17:55:05.000Z"
score: 81
channel: "ai"
tags: ["Cortex","VLA","具身智能","长程操作","零样本泛化"]
---

# Cortex：一种双向对齐的具身智能体框架，实现长程操作

## AI 点评

> Cortex最吸引我的是它将高层语义规划与底层运动控制之间的鸿沟用一套精巧的技能原语和可处理性原则填平了。这不仅是一篇论文，更像是一个可落地的系统设计——尤其是零样本完成化学实验的案例，让人看到通用机器人操作的可能性。对从事机器人学习、VLA模型研究和工业自动化应用的人来说，这是值得细读的工作。

## 速览

Cortex是一个双向对齐的具身智能体框架，通过标准化32种技能基元并注入可处理性原则，将高层视觉-语言模型（VLM）的规划语义与低层视觉-语言-动作（VLA）模型的执行运动学无缝衔接。该框架利用4000小时开源视频数据和30小时模拟数据自动注释训练，采用事件平衡采样策略微调，在Libero-long和RoboTwin基准上分别提升3.1%和4.1%，并零样本完成多阶段化学实验等未见真实世界任务。

## 关键点

- Cortex统一了32种操作技能基元，并引入可处理性原则，解决了高层规划与低层执行的语义鸿沟。
- 自动标注超4000小时开源视频数据并生成30小时模拟数据，实现大规模训练数据构建。
- 事件平衡采样策略有效处理子任务转换中的规划歧义，提升长程任务鲁棒性。
- 零样本泛化到新颖真实世界任务（如化学实验），证明其通用性远超单独VLA微调。

## 全文

While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations. Hierarchical dual-system methods address this but suffer from a gap between high-level planning semantics and low-level execution kinematics. We introduce Cortex, a bidirectionally aligned embodied agent framework with a customized planning interface that conveys executable and tractable subtask plans from high-level VLM to low-level VLA. Specifically, we standardize manipulation subtasks into 32 canonical skill primitives and inject tractability principles, such as representative object attributes and improved trajectory reachability, into the data generation pipeline. This enables automatic annotation of over 4k hours of open-source video data and generation of 30 hours of simulation data. We further devise an event-balanced sampling strategy to construct training data for fine-tuning the framework to better handle planning ambiguity during subtask transitions, enhanced by carefully designed harness engineering from task contexts to skill constraints during inference. Both open-loop VLM and closed-loop system evaluations demonstrate Cortex's efficacy, e.g., it outperforms monolithic baselines by 3.1% on Libero-long and 4.1% on RoboTwin. Notably, Cortex's generalist VLM enables zero-shot completion of unseen real-world long-horizon tasks, such as multi-stage chemistry experiments, by simply combining with a fine-tuned VLA-a capability infeasible through VLA fine-tuning alone.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_7a3ae66350397ad980c4d73c