arXiv：cs.AI· Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian, Yuting Xu, Fei Wang, Shiao Liu, Wei Zhang, Xiaolong Wu, Wenbin Tang, Zedong Chu, Mu Xu·· 17 小时前
ABot-ER：通过智能体数据-模型协同进化实现统一具身推理
ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
AI 导读
ABot-ER 是一个统一具身推理基础模型，在感知、规划、执行三项能力上均达到专家级深度，并在覆盖三大核心能力、五个能力维度的十二个基准上取得统一参数框架下的 SOTA 综合表现。
正文
Authors:Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian, Yuting Xu, Fei Wang, Shiao Liu, Wei Zhang, Xiaolong Wu, Wenbin Tang, Zedong Chu, Mu Xu
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18355 [cs.AI] |
| (or arXiv:2610.18355v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18355 arXiv-issued DOI via DataCite |
Submission history
From: Heng-Da Xu [view email]
[v1]
Tue, 13 Oct 2026 13:21:56 UTC (6,076 KB)
[v2]
Wed, 14 Oct 2026 06:44:13 UTC (6,076 KB)
来源：arXiv：cs.AI · arxiv.org