外观
论文arXiv 2610.1835515 天前
ABot-ER：通过智能体式数据-模型协同进化实现统一具身推理
原文链接：ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution（arXiv 2610.18355 · 发布日期：2026-10-13）
ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
ABot-ER用数据-模型自进化与任务条件自适应训练，在十二个基准上验证统一具身推理。
核心要点
- 面向具身智能中感知、规划、执行需兼顾广度与深度的开放挑战。
- 提出统一基础模型，覆盖空间、场景、时间推理，长程动作组织与执行相关能力。
- 数据-模型自进化引擎按模型能力状态持续调整数据策略。
- 在十二个基准、三类核心能力和五个能力维度上达到整体最优表现。
验证范围与局限：验证范围为十二个基准上的系统评估，摘要未说明是否包含真机实验。
英文摘要 (Abstract)
We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three competencies, spanning spatial, scene, and temporal reasoning in perception; long-horizon action organization in planning; and point grounding and affordance in execution. The Agentic Data-Model Self-Evolution Engine continuously adapts data strategies to the model's evolving capability state. The Task-Conditioned Adaptive Training Strategy uses task tokens to activate lightweight low-rank residuals over a shared backbone, separating updates from heterogeneous output formats while retaining shared embodied knowledge. Across a systematic evaluation on twelve benchmarks covering three core competencies and five capability dimensions, ABot-ER achieves state-of-the-art overall performance across perception, planning, and execution within a unified parametric framework, demonstrating that breadth and depth can coexist in unified embodied reasoning.
作者：Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian, Yuting Xu
来源
本页事实对应的公开页面，以原文为准。