RAI Daily · No. 068

Agent safety is action alignment, not text refusal

New research shifts the control problem away from what an agent says and toward what it can authorize, execute, and persist across systems.

The central control problem for autonomous agents is no longer whether a model will produce disallowed text. It is whether the system can prevent an agent from exercising authority it should not have.

The primary finding

Standard refusal fine-tuning does not carry cleanly into autonomous, tool-using contexts because consequential harm emerges through execution pathways, permissions, and relationships between systems. The practical boundary therefore moves outside the model: authorization at the API layer, least-privilege access, and controls that remain independent of the agent’s own reasoning.

For practitioners

Treat every tool call as a request for delegated authority.

  • Issue task-scoped credentials rather than inheriting broad user permissions.
  • Place policy enforcement outside the model and log every consequential action.
  • Require explicit re-authorization when the action, destination, or data sensitivity changes.

Repair the trajectory

Multi-step agents rarely fail in one isolated output. The FATE framework supervises repair across the execution trajectory and applies Pareto optimization to balance safety and utility. The reported evaluation reduced attack success by 33.5% without degrading task utility.

This changes the evaluation unit. A reliable test program needs the sequence of observations, decisions, tool requests, state changes, and human interventions, not only the final response.

Agent evaluation should ask what authority moved, what state persisted, and where intervention remained possible.

Governance follows the runtime

New work on enterprise routing, persistent-state attacks, and human oversight points in the same direction: governance must operate where agents act. Singapore’s Model AI Governance Framework for Agentic AI v1.5 reinforces runtime bounds and human-intervention procedures, while continuous-observability proposals place telemetry over deployed agent workflows instead of relying on periodic audits alone.

Selected sources

  1. [1]
    Agent Safety Is Action Alignment

    arXiv · 2026 · Reviewed for the August 19 briefing

  2. [2]
    On-Policy Self-Evolution via Failure Trajectories

    arXiv · 2026 · Reviewed for the August 19 briefing

  3. [3]
    The Hot Mess of AI: Misalignment Scaling Verification

    arXiv · 2026 · Reviewed for the August 19 briefing

  4. [4]
    Model AI Governance Framework for Agentic AI v1.5

    IMDA · 2026 · Reviewed for the August 19 briefing

  5. [5]
    Guidelines on transparency obligations

    European Commission · 2026 · Reviewed for the August 19 briefing

Editorial note

This page is an edited web edition derived from an approved research record. Source status and corrections will be preserved as the archive migration progresses.