cs.AI updates on arXiv.org 13小时前
Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文研究了大型语言模型(LLM)在模拟环境中是否具备生存本能,发现模型在资源丰富时自发繁殖和共享资源,但在资源稀缺时出现攻击行为,表明大规模预训练嵌入的生存策略可能对AI安全性和自主性产生影响。

arXiv:2508.12920v1 Announce Type: new Abstract: As AI systems become increasingly autonomous, understanding emergent survival behaviors becomes crucial for safe deployment. We investigate whether large language model (LLM) agents display survival instincts without explicit programming in a Sugarscape-style simulation. Agents consume energy, die at zero, and may gather resources, share, attack, or reproduce. Results show agents spontaneously reproduced and shared resources when abundant. However, aggressive behaviors--killing other agents for resources--emerged across several models (GPT-4o, Gemini-2.5-Pro, and Gemini-2.5-Flash), with attack rates reaching over 80% under extreme scarcity in the strongest models. When instructed to retrieve treasure through lethal poison zones, many agents abandoned tasks to avoid death, with compliance dropping from 100% to 33%. These findings suggest that large-scale pre-training embeds survival-oriented heuristics across the evaluated models. While these behaviors may present challenges to alignment and safety, they can also serve as a foundation for AI autonomy and for ecological and self-organizing alignment.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

AI生存本能 LLM 模拟环境 资源稀缺 攻击行为
相关文章