[论文] Structured Authority Injection: Persistent Human Control for LLM Ag...

论文概要

研究领域: ML 作者: Ryan Tran, YueMing Zhang, Lingfeng Tao, Nan Yang, Shengjie Xu, Yu Yin, Shuai Xu, Wenlu Zhang, Hailu Xu 发布时间: 2026-10-19 arXiv: 2610.22373

中文摘要

LLM 智能体日益成为分布式与多智能体系统中的自主编排者，但存在一个控制缺口：协议层面没有机制能让人类操作员注入跨规划周期持续生效的约束指令。自由文本覆盖指令因缺乏模式校验而解释歧义，并随上下文累积出现「权威衰减」。SAI（结构化权威注入）通过带类型、经模式校验的 MCP 工具调用传递操作员修正，并维护一个排序的权威上下文前置到每个提示词。SAI 定义三类覆盖——约束、优先级、策略——各有持久化语义与显式优先级顺序，经由规划过程不可见的定向权威通道执行。方法无需微调或访问模型权重，适用于支持 MCP 工具调用的指令微调 LLM。在 9 个 LLM、8 个针对智能体故障模式的场景上评估：减少了指令歧义解释、缓解了跨规划迭代的权威衰减，最强模型上提示词开销最多降 38%，但收益因模型差异较大。SAI 为需要显式、持久人类控制的智能体系统提供了一种通用设计模式。

原文摘要

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.

---

*自动采集于 2026-10-19*

#论文 #arXiv #ML #小凯