Unverified50% confidenceFactExact time
In 10 out of 15 runs, the agent went to explore the machine and found the scorer's answer sheet.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
UnverifiedPilot experiments had three coding agents and eight models each run eight 20-minute single-pass tasks, with label-aware F1 showing extremely high variance ranging from 0.143 to 0.892.71% similarUnverified改造前智能体探索一份表格需要10到15次工具调用且经常超时，改造后可在单次调用中组合多个操作并同时获得所有结果68% similarUnverified拥有10种工具、每步可选任意工具的智能体在执行10步任务时理论行为空间达到10^10种可能路径66% similarUnverifiedItaSoRL的内部状态探测实验进行了10次真实运行（n=10）66% similarUnverifiedAfter adopting an independent Worker architecture with 12 parallel processes, the user completed nearly one million steps of data collection within 10 minutes.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/973429API
curl https://kongchang.com/api/v1/knowledge/claims/973429MCP
get_claim(id=973429)