AutoPersonas：用于开放式角色演变的多时间尺度循环引擎
A Multi-Timescale Recursive Self-Improvement Engine for Open-Ended Persona Growth
浏览论文内容
中文总结 AI 辅助
研究长期角色代理在适应新情况时的自我锁定问题，提出多时间尺度生活环境引擎AutoPersonas，通过分离环境与角色状态等，经模拟和测试验证，该方法可减少自我锁定并保持身份连续性。
中文摘要 AI 辅助
长期的角色代理在适应新事件、关系、证据和社会条件时必须保持可识别。我们将自我锁定识别为持续角色生命周期循环中的运行时故障模式：局部合理的事件不断出现，而生成的生活却朝着熟悉的环境、薄弱的关系、悬而未决的决策和陈旧的生活阶段崩溃。我们将此故障追溯到模型级向高概率行为通道的收敛以及来自状态、记忆、历史和环境摘要的系统级上下文引力。我们引入了AutoPersonas，这是一个用于有界角色级递归自我进化的多时间尺度生活环境引擎。它将环境方面的事件、累积的观察结果和角色状态分开。其OSO循环允许面向未来的发散性内容，同时要求在状态或可达性改变之前进行由证据控制的吸收。一个三年的压缩模拟揭示了环境水印外壳、事件强化差距、慢变累积故障递归犹豫不决和薄弱关系持久性问题。一个八模型40天的压力测试生成了1600个事件，发现平均滚动5天的动作类别重复率为95.2%-97.6%，所有模型在第11天均超过90%。语义重新保留发现在所有直接循环运行中宏观主题重复率为79.0%-88.0%。在同一运行时40天的A/B测试中，上下文切片屏蔽加上针对每个样本的发散目标将宏观主题重复率从61.8%降低到36.3%，并使累积主题数量大致翻倍。一个少年妖精虚构世界运行在没有硬现实世界干扰的情况下重现了反固定机制。这些结果支持了一个有界的主张：将受控发散与证据控制的吸收分开可以减少角色-环境自我锁定，同时保持身份连续性。
英文摘要
Role-playing AI personas today do not grow: they hold a fixed character, so the relationship a user builds with them has nothing to accumulate on. We introduce AutoPersonas, a multi-timescale engine that applies recursive self-improvement (RSI) to persona growth: rather than improving its intelligence, the persona recursively revises the State, evidence, and life-environment that shape its own future. We identify self-locking as the runtime failure mode of this recursion: locally plausible events keep appearing while the generated life collapses toward familiar environments, weak relationships, suspended decisions, and stale life stages. We trace it to model-level convergence toward high-probability behavioral channels and system-level context gravity from State, memory, history, and environment summaries. A three-year compressed simulation exposed environment watermark shells, occurrence-hardening gaps, slow-change accumulation failures, recursive indecision, and weak relationship persistence. An eight-model 40-day stress test generated 1,600 events and found mean rolling 5-day action-category repetition of 95.2%-97.6%, with all models crossing 90% by day 11; semantic re-keeping found 79.0%-88.0% macro-theme repetition. The primary contribution is the definition and measurement of self-locking. We also report a mitigation as a black-box result, with internals withheld for commercial reasons: in a same-runtime 40-day A/B, our production divergence configuration reduced macro-theme repetition from 61.8% to 39.4% and nearly doubled cumulative theme count, and a juvenile-goblin fictional-world run reproduced this regime without hard real-world intrusions.
