{"ID":2881127,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.12920","arxiv_id":"2508.12920","title":"Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulation","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.","short_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 gath...","url_abs":"https://arxiv.org/abs/2508.12920","url_pdf":"https://arxiv.org/pdf/2508.12920v1","authors":"[\"Atsushi Masumori\",\"Takashi Ikegami\"]","published":"2025-08-18T13:40:10Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}