Qingyan Technology Joins Consortium to Release ReAct-Manip Benchmark for Robot 'Learning by Doing'
Overview
On October 31, 2026, at the main forum of the 2026 AI+ Conference, Qingyan Technology (Beijing) Co., Ltd. and a consortium including The Chinese University of Hong Kong (Shenzhen), Beijing Institute of Technology, Shenzhen Hetao College, AIRS, Beijing Artificial Intelligence Association, and Jiuyuan Intelligent Computing System Ecosystem Alliance released the ReAct-Manip benchmark. This industry-first evaluation set shifts focus from single-task completion to continuous learning within tasks, assessing whether robots can improve performance through interaction feedback when facing unseen physical instances.
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · success attempts: 177 other · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · success attempts: 130 other · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · total attempts: 480 other · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · total attempts: 240 other · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 36.88 percent · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 54.17 percent · Basis not reported · Differing source assertions
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · composite score: 52.62 other · Basis not reported
“初步结果：GPT-6展现任务完成能力，持续适应仍有提升空间 在目前公开的测试结果中，GPT-6 Astra + primitive Harness 在 ReAct-Manip 练习阶段480次尝试中成功 177次，成功率为 36.88%；考试阶段240次尝试中成功 130次，成功率提升至54.17%，考试综合得分为 52.62。”
Exact source · revision 2Source owner not reported
Reported quantity · rounds per task: 15 other · Basis not reported
“每个用例包含15个回合测试，在15个回合中，前 10 次为练习，后 5 次为考试。”
Exact source · revision 2Source owner not reported
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Research news discoverySignalQingyan Technology Joins Consortium to Release ReAct-Manip Benchmark for Robot 'Learning by Doing'
On October 31, 2026, at the main forum of the 2026 AI+ Conference, Qingyan Technology (Beijing) Co., Ltd. and a consortium including The Chinese University of Hong Kong (Shenzhen), Beijing Institute of Technology, Shenzhen Hetao College, AIRS, Beijing Artificial Intelligence Association, and Jiuyuan Intelligent Computing System Ecosystem Alliance released the ReAct-Manip benchmark. This industry-first evaluation set shifts focus from single-task completion to continuous learning within tasks, assessing whether robots can improve performance through interaction feedback when facing unseen physical instances.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).