← All parts of this equation

Equation 2 · Part 4 · Measuring AI Agent Architectures: Evidence, Benchmarks, and Uncertainty

Symbol p_all k succeed

pat least one of k=1−(1−p)k,pall k succeed=pk.p_{\text{at least one of } k} = 1 - (1-p)^k, \qquad p_{\text{all } k \text{ succeed}} = p^k.
pall k succeedp_{\text{all } k \text{ succeed}}

What this part means

pap_all k succeed is one of the signed contributions combined to compute the quantity on the left.

Its job in the formula

pap_all k succeed is one of the signed contributions combined to compute the quantity on the left.

The passage around this formula

The distinction matters because the two metrics behave very differently even under the most favourable possible assumption — that trials are statistically independent. Write p for the probability that a single trial on a given task succeeds. Under independence, pat least one of k=1−(1−p)k,pall k succeed=pkp_{\text{at least one of } k} = 1 - (1-p)^k, \qquad p_{\text{all } k \text{ succeed}} = p^k. The first quantity rises quickly toward one as k grows, which is the intuitive but misleading sense in which “just try again” seems to fix unreliability. The second quantity falls quickly toward zero, and it is the quantity that matters if a task must be completed correctly on a specific occasion rather than merely being solvable in principle across several attempts.

Read this part in the article →

Learn the underlying idea

A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? guide →

See this notation across published equations →

Sources cited in the article section

These citations provide research context; check each source for the exact claim it supports.