# A Multi-Timescale Recursive Self-Improvement Engine for Open-Ended Persona Growth

arXiv: https://arxiv.org/abs/2607.08252 · HTML: https://mlsanity.com/paper/2607.08252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)
- [Humanoid Agents: Platform for Simulating Human-like Generative Agents](https://mlsanity.com/paper/2310.05418/) (2023)
- [One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity](https://mlsanity.com/paper/2411.04427/) (2024)
- [Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World](https://mlsanity.com/paper/2410.16713/) (2024)
- [The Price of Format: Diversity Collapse in LLMs](https://mlsanity.com/paper/2505.18949/) (2025)
- [Position: Model Collapse Does Not Mean What You Think](https://mlsanity.com/paper/2503.03150/) (2025)
- [A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops](https://mlsanity.com/paper/2502.18865/) (2025)
- [Group-Aware Reinforcement Learning for Output Diversity in Large Language Models](https://mlsanity.com/paper/2511.12596/) (2025)

## Built on by (most cited first, 1 of 1)

- [Self-Emergence Agent Architecture:Behavior-Inertia HMM, Reflexive Metacognition,and Social-Contrastive Self-Modeling](https://mlsanity.com/paper/2609.17331/) (2026)

## Abstract (arXiv)

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.