الملخص
General-purpose agents can plan, use tools, and revise their behavior from feedback, but it remains unclear whether these capabilities transfer from digital environments to embodied manipulation. To investigate this question, we introduce LIBERO-Agent, an agent-native benchmark for evaluating these agents in robot manipulation tasks. Rather than asking agents to submit task-level Python control programs or operate through high-level robot skills, LIBERO-Agent provides an interactive robotic environment where agents can select which observations to inspect, process them with their own tools, and issue native action commands. LIBERO-Agent integrates 200 tasks into a common interaction framework and provides a 30-task primary suite that separates perception, short-horizon execution, and long-horizon composition. Results reveal a pronounced reliability gap: while agents perform well on perception and easy short-horizon tasks, their performance degrades substantially on hard short-horizon and long-horizon tasks. Richer observations improve short-horizon manipulation, while demonstration benefits depend on the agent and format. Among these agents, GPT-6 Astra achieves the strongest overall performance. Further analysis shows its major advantage lies in mechanism interaction, especially when sustained physical contact is needed, while its remaining failures stem from cross-stage interference and geometric errors.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Diao, Z., Chen, Y., Xie, S., Lu, T., Peng, W., Zhong, G., Xu, H., Ye, Z., Wu, Z., & Jiang, Y. G. (2026). LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation. https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation
MLA 9
Diao, Zijie, et al. "LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation." https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation.
شيكاغو (المؤلف–التاريخ)
Diao, Zijie, Yitong Chen, Sicheng Xie, Tianyi Lu, Wujian Peng, Guojin Zhong, Houze Xu, Ziyi Ye, Zuxuan Wu, and Yu-Gang Jiang. 2026. "LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation." https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation.
هارفارد
Diao, Z., Chen, Y., Xie, S., Lu, T., Peng, W., Zhong, G., Xu, H., Ye, Z., Wu, Z. and Jiang, Y. G. (2026) 'LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation', Available at: https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation.
فانكوفر
Diao Z, Chen Y, Xie S, Lu T, Peng W, Zhong G, et al. LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation. https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation
IEEE
Z. Diao, Y. Chen, S. Xie, T. Lu, W. Peng, G. Zhong, H. Xu, Z. Ye, Z. Wu, and Y. G. Jiang, "LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation," https://omanscience.com/ar/articles/libero-agent-evaluating-general-purpose-agents-for-direct-embodied-manipulation.