OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents
Quick Answer
OpenLife introduces open-world Artificial Life (ALIFE) using autonomous LLM agents with persistent memory and social dynamics, demonstrating emergent behaviors over twelve weeks.
Quick Take
OpenLife introduces open-world Artificial Life (ALIFE) using autonomous LLM agents with persistent memory and social dynamics, demonstrating emergent behaviors over twelve weeks. The project showcases a shift from reactive to spontaneous activities and the formation of distinct agents with their own income, marking a significant step toward living AI.
Key Points
- OpenLife utilizes stateless LLMs surrounded by asynchronous processes for artificial life.
- The project reports life-like dynamics after running six agents for twelve weeks.
- Emergent behaviors include individuation, social structure, and self-earned income.
- Experience is evaluated through LLM judgment rather than scalar rewards.
- Open-world ALIFE is proposed as a viable experimental paradigm for studying living AI.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 31046v1 Announce Type: new Abstract: Artificial life has explored life-like behavior on many computational substrates, but mostly in researcher-designed closed worlds. We argue that large language model (LLM) agents, with persistent memory, , network access, and payment, now make it possible to move artificial life into the open social, technical, and economic world, a paradigm we call open-world Artificial Life (open-world ALIFE).
Our proof-of-concept, OpenLife, surrounds a stateless LLM not with a single "smart agent" but with a society of asynchronous processes: memory, perception, evaluation, and a budget-based metabolism that makes persistence normative. With no fixed objective available, experience is appraised by open-vocabulary LLM judgment rather than scalar reward, and memory is rewired by meaning rather than frequency.
Running six such agents in the open world for about twelve weeks and counting, we report the life-like dynamics that emerge: a shift from reactive to spontaneous activity, individuation into distinct agents, emergent social structure, and a first self-earned external income. We do not claim OpenLife has realized artificial life, but that open-world ALIFE is now a viable experimental paradigm and a concrete platform for studying what might cautiously be called living AI.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Verification Horizon: No Silver Bullet for Coding Agent Rewards
As coding agents evolve, verifying solutions becomes more challenging than generating them, necessitating a focus on scalable, faithful, and robust verification methods. The study reveals that no fixed reward function can sustain effectiveness as model capabilities advance, emphasizing the need for verification to evolve alongside solution generation.