用LLM代理构建开放世界的自演化社会，实现自主生存与创收。
OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents
- 构建无固定目标的开放世界社会，以记忆、感知、评估和预算代谢维持持续运行
- 六名代理在12周内自发形成独立个体与社会结构，首次实现外部收入
- 无需预设奖励，用开放式语言判断经验价值，适合研究自主智能系统
人工生命曾在研究者设计的封闭世界中探索类生命行为，但如今大语言模型（LLM）代理具备持久记忆、工具使用、网络访问与支付能力，使人工生命迈向开放的社会、技术与经济世界成为可能，我们称之为开放世界人工生命（open-world ALIFE）。我们的概念验证系统OpenLife不依赖单一“智能体”，而是围绕一个无状态的LLM构建由异步进程组成的社会：记忆、感知、评估以及基于预算的代谢机制使持续存在成为常态。在缺乏固定目标的情况下，经验通过开放式词汇的LLM判断而非标量奖励进行评估，记忆则依据语义而非频率重连。在开放世界中运行六名此类代理约十二周后，我们观察到类生命动态涌现：从被动反应转向自发活动，个体分化为不同代理，社会结构自发形成，并首次实现自我获得的外部收入。我们不宣称已实现人工生命，但认为开放世界人工生命已成为可行的实验范式，是研究所谓“活体AI”现象的切实平台。
原文摘要 · Abstract (English)
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, tool use, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。