Researchers propose Structured Authority Injection to enforce persistent human control in LLM agent systems

LLM-based agents are increasingly used as autonomous orchestrators in distributed and multi-agent systems, yet a control gap remains: no protocol-level mechanism allows human operators to inject binding directives that persist across planning cycles.

Free-text overrides suffer from ambiguous interpretation due to lack of schema validation and from authority erosion as operator instructions lose influence within accumulating context.

The authors propose Structured Authority Injection (SAI), a protocol that routes operator corrections through typed, schema-validated Model Context Protocol (MCP) tool calls and maintains a ranked authority context prepended to each LLM prompt.

SAI defines three override classes—Constraint, Priority, and Strategy—with distinct persistence semantics and an explicit precedence order enforced via a directed authority channel inaccessible to the planning process.

The method requires no model fine-tuning or access to model weights and applies to instruction-tuned LLMs supporting MCP tool use.

Evaluation across nine LLMs and eight scenarios targeting agent failure modes showed reduced ambiguous directive interpretation and mitigated authority decay across planning iterations.

Prompt overhead benefits were observed in the strongest models, with up to 38% lower overhead depending on model and scenario, though benefit varied substantially across models.

The authors describe SAI as a general design pattern for agent systems requiring explicit and persistent human control.