1_introduction · 完整稿件源码

\section{Introduction}
A coding agent that has produced a patch still faces a consequential decision: submit it, inspect another test result, keep editing, or start over. These actions spend different resources and expose the agent to different information. A useful controller must predict what an action will accomplish, rather than treating every uncertain patch as a reason to spend more compute.

Patch correctness is an incomplete target for this decision. Consider two patches with the same probability of passing the official evaluator. The first has a localized error that a short regression test can expose. The second depends on a mistaken interpretation of the issue, so repeating nearby tests supplies little useful information. Their current correctness probabilities can be equal even when the best next actions differ. Conversely, a test that reliably reports a failure need not provide feedback that the repair model can use. The value of verification depends on the code state, the diagnostic, and the model that receives it.

Prior work has established several components of this problem. Lightweight monitors can predict failing software-agent trajectories and trigger restarts \citep{wang2026failfastrestartsmartearlyfailure}. Bayesian controllers choose criticism, refinement, verification, and stopping using cost-sensitive beliefs \citep{papamarkou2026bayesiancontrolcodingagents}. Execution-free reward models distinguish candidate patches, while learned testing agents improve the feedback available to a repair agent \citep{shum2025swermexecutionfreefeedbacksoftware,tao2026execcriticlearntesttest}. These results make a stronger question possible: does directly learning the outcome of each intervention improve control over learning current correctness and then applying an action rule?

Figure~\ref{fig:method} summarizes the proposed pipeline. We formulate the decision as supervised action-value estimation at a repair boundary. A fixed generator produces a candidate patch. A small controller then chooses one of five bounded actions. During data collection, each nonterminal action is actually executed from the same restored candidate state, with a fresh environment and a prescribed random seed. An official evaluator labels only the final patch. The decision model learns a separate success probability and cost prediction for each action. The probabilities are not a categorical distribution: several actions may succeed, or all may fail.

This design keeps the learning problem narrow. The repair model remains fixed, the test menu is determined before action execution, and all continuation actions receive the same token and tool-call limits. The comparison can therefore isolate the supervisory target without attributing changes in the repair model or additional sampling to the controller. A smaller classification error is useful only if the resulting choices improve the task-level success--cost relationship.

The implemented contribution consists of an executable same-state intervention protocol, a non-generative action-outcome model, and a matched evaluation that separates verification choice from recovery control. The initial evidence establishes the execution pipeline: 12 candidate verdicts are reproduced exactly, and 24 public-test calls complete. The controlled outcome comparison is the decisive experiment, because infrastructure correctness and useful agent intervention answer different questions.