Unverified50% confidenceFactExact time
Under the i.i.d. assumption, the success rate of an n-step task is the single-step accuracy p raised to the nth power.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the Best-of-N strategy, if the probability of success in a single sample is p, then the probability of at least one success in N independent samples is 1-(1-p)^N, which approaches 1 as N increases.78% similarUnverifiedThe overall success rate of an n-step trajectory is the nth power of the per-step success rate p (p^n), which is the exponential decay of compound probability.77% 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.70% similarUnverifiedThe benchmark produces two numbers for each model that are never merged: a task score and a false-confidence rate (the proportion of cases that should have been escalated but were answered anyway).69% 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）69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1116266API
curl https://kongchang.com/api/v1/knowledge/claims/1116266MCP
get_claim(id=1116266)