Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides

A new arXiv paper (2610.22373v1) proposes Structured Authority Injection (SAI), a protocol that routes human operator corrections to LLM agents through typed, schema-validated Model Context Protocol (MCP) tool calls and prepends a ranked authority context to each prompt. SAI defines three override classes — Constraint, Priority and Strategy — with distinct persistence semantics and a precedence order enforced through a directed authority channel the planning process cannot access, requiring no model fine-tuning or weight access. Across nine LLMs and eight scenarios targeting agent failure modes, the authors report reduced ambiguous directive interpretation and mitigated authority decay across planning iterations, with prompt overhead lower in the strongest models by up to 38% depending on model and scenario, though benefit varied substantially across models.

arXiv:2610.22373v1 Announce Type: new Abstract: 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. We propose Structured Authority Injection SAI , a protocol that addresses these issues by routing operator corrections through typed, schema-validated Model Context Protocol MCP tool calls and maintaining 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 shows reduced ambiguous directive interpretation and mitigated authority decay across planning iterations, with lower prompt overhead in the strongest models up to 38% depending on model and scenario , though benefit varies substantially across models. SAI provides a general design pattern for agent systems requiring explicit and persistent human control.