RefineAct

A runtime verification framework for checking an LLM agent's proposed actions before execution.

First author ASE 2026 Runtime verification

RefineAct studies LLM-agent reliability at the boundary between proposed action and executed action. It inserts a runtime verification layer that checks whether a candidate action is consistent with the task intent before the action is allowed to affect the environment.

Problem

Standard agent frameworks can execute a tool action as soon as the model produces it. If the action is unsafe or inconsistent with the task, the error may become visible only after the environment has already changed.

Approach

RefineAct inserts a verification layer between action generation and execution. Candidate actions are checked against a task-intent specification, and rejected actions are regenerated before they can run.

Results

The work is reported in an ASE 2026 paper, and the public lightweight implementation is linked as aligned while the full paper artifact is prepared for release.

Why it matters

Checking actions at runtime provides an auditable control point for agent behavior, complementing prompt design and model training with an execution-time reliability mechanism.

The formal approach and complete evaluation are in the paper (Batole et al., 2026).

References

2026

  1. RefineAct: Automatic Runtime Verification of LLM Agent Actions
    Fraol BatoleFoutse Khomh, and Hridesh Rajan
    In 2026 IEEE/ACM International Conference on Automated Software Engineering (ASE), Jan 2026