发表机构
Gubernaut Research（Gubernaut研究）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对大语言模型代理的故障模式，提出Gubernaut认知控制器，通过在四个前沿模型上预注册的评估协议验证，该控制器能使模型更平静，有恢复特征等机制，附带可重判记录及预注册故障模式。
AI 中文摘要
大语言模型代理存在反应性故障模式，如挑衅下升级、奉承下谄媚漂移、卡住时固执。这些是倾向故障而非能力故障。本研究提出Gubernaut认知控制器（GCC），是Nelson-Narens监控控制回路中与模型无关的运行时控制层。对象层读写文本，确定性元层仅读取数值遥测数据并返回调节姿态。通过预注册的一次生成/多次判断协议在四个前沿模型矩阵上评估GCC，调节后的模型在多数情况下更平静，有恢复特征等机制，还附带可重判的记录和面板，预注册了五种故障模式。
英文摘要
Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck. These are failures of propensity, not capability; they concern what a model does under sustained pressure, which training-time alignment reduces but does not eliminate at runtime. This research led to the Gubernaut Cognitive Controller (GCC), a model-agnostic runtime control layer in a Nelson--Narens monitoring--control loop: an object level reads and writes text, while a deterministic meta level reads only the numeric telemetry {intensity, valence, repetition} and returns a regulating posture. Because the meta level ingests zero tokens, no injection channel to the controller exists by construction (an architectural property, not yet adversarially tested); the text-exposed arbiter's compliance is measured, not assumed. We evaluate the GCC with a pre-registered, generate-once/judge-many protocol across a 4x4 matrix of four frontier models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3), each serving as both a generator and a judge. The regulated arm is calmer in 13 of 16 cells at p<.05 and 15 of 16 by sign; the three sub-threshold cells, including a -0.04 null, all fall on the single near-saturated host. The effect survives a lineage-independent fourth judge family (xAI), strong evidence that it is no artifact of shared judge style. The clearest mechanism is the recovery signature: arousal that integrates under attack and then decays, valence-gated, on de-escalation, replicating across all four families. Transcripts and panels ship with SHA-256 provenance and are re-judgeable; five failure modes are pre-registered. No consciousness claims are made.
Comments26 pages, 7 figures, 3 tables. Data, transcripts, and analysis scripts: https://github.com/thegubernaut/Gubernaut_Validation Project page: https://gubernaut.com (archived at https://doi.org/10.5281/zenodo.21303518)
