≤

The passage around this formula

At an agent step k , a model receives an observation history $o_{\le k}$ , task goal g , and harness state $h_k$ , then proposes an action: $a_k \sim \pi_{\theta}(a\mid o_{\le k},g,h_k)$. 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 →