Expired50% confidenceBenchmarkExact time
When an agent task exceeds 10 steps, the task completion rate of mainstream large language models exhibits a nonlinear decline.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/19/2026(expired)
Sources
Related Claims
UnverifiedTypical failure patterns of AI Agents on complex tasks include: performing well in the first ten minutes, drifting off target after half an hour, and producing completely unusable output after two hours.70% similarUnverifiedIn enterprise applications, when building automated workflows containing over a dozen steps, any skipped step can cause the entire process to break down, making a model's instruction-following capability especially critical.69% similarUnverifiedInstalling more than 100 Agents causes the system to run slowly and token consumption to explode; 3–5 Agents with clearly defined responsibilities are superior to 100 Agents.67% similarUnverified以Mythos Preview为例，成功率在4小时任务节点开始显著下滑，且在15分钟内的短任务中某些类别模型也无法稳定完成67% similarUnverifiedAgent tasks require multiple model invocations, and a 12B model on a consumer-grade GPU already takes several seconds per inference, causing the time cost of multi-step tasks to accumulate significantly.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/575925API
curl https://kongchang.com/api/v1/knowledge/claims/575925MCP
get_claim(id=575925)