Unverified50% confidenceFactExact time
The experiment targeted a brushless DC (BLDC) actuator, with 120 agents distributed across 4 automated research sessions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/9/2026
First Seen
Valid until: 11/7/2026
Sources
120个AI智能体1.5小时完成数周硬件研究：Onyx开源项目实测
Related Claims
UnverifiedThe tested task was conducted over four rounds, dispatching a cumulative total of 68 sub-agents to complete batch prompt testing for a digital human writing skills module.71% similarUnverifiedIn actual testing, one Deep Research call invoked 104 agents for targeted research, completing fact-checking based on 22 sources and 59 claims.65% similarUnverifiedCodex使用了126个子智能体、32500次工具调用、391次浏览器测试和2300多次单元测试；Claude Code使用35个子智能体、102次浏览器测试和296次单元测试63% similarUnverifiedThe proof was completed by coordinating 64 parallel sub-agents working collaboratively, with a dedicated adversarial agent introduced to verify the reasoning chain.63% similarUnverified字节跳动发布EdgeBench基准测试，用于评估自主AI Agent的长期学习能力，涵盖134个跨6大类别任务，已公开51个任务61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/714579API
curl https://kongchang.com/api/v1/knowledge/claims/714579MCP
get_claim(id=714579)