Unverified50% confidenceBenchmarkExact time
在歧义点的四类行为中，'先搜再问'成功率最高，平均通过率达93.4%，远高于'直接猜'的56.5%，'搜多次再猜'为51.5%
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
Related Claims
Unverified假设每步成功率为95%，在一个50步会话中整体成功率约为0.95^50≈8%72% similarUnverifiedSelf-Consistency通过多次采样推理路径后投票取多数答案，可进一步提升准确率约5-10个百分点70% similarVerified如果一个10步操作中每步准确率为95%，整体成功率仅约60%70% similarUnverified每步60%准确率意味着连续5步后整体成功率约为7.8%（0.6的5次方）70% similarVerifiedReAct's errors amplify in a chain: if the accuracy per step is p, the overall success rate after n steps is approximately p to the power of n; with a per-step accuracy of 95%, the overall success rate drops to approximately 59.9% after 10 steps and only 35.8% after 20 steps.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/387237API
curl https://kongchang.com/api/v1/knowledge/claims/387237MCP
get_claim(id=387237)