← All parts of this equation

Equation 14 · Part 3 · OpenAI Codex as a Software-Engineering System: Models, Harnesses, and Evidence

Symbol a

ak∼πθ(a∣o≤k,g,hk).a_k \sim \pi_{\theta}(a\mid o_{\le k},g,h_k).
aa

What this part means

a is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Its job in the formula

a is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

The passage around this formula

At an agent step k , a model receives an observation history o≤ko_{\le k} , task goal g , and harness state hkh_k , then proposes an action: ak∼πθ(a∣o≤k,g,hk)a_k \sim \pi_{\theta}(a\mid o_{\le k},g,h_k). The action might request a file read, search, patch, shell command, test, browser interaction, or delegation. It is not yet an environmental transition. The harness parses the proposal, checks that it matches an available tool schema, applies policy, executes permitted operations, and converts results into the next observation.

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value 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.