{"ID":2871071,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12190","arxiv_id":"2509.12190","title":"Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm","abstract":"When survival instincts conflict with human welfare, how do Large Language Models (LLMs) make ethical choices? This fundamental tension becomes critical as LLMs integrate into autonomous systems with real-world consequences. We introduce DECIDE-SIM, a novel simulation framework that evaluates LLM agents in multi-agent survival scenarios where they must choose between ethically permissible resource , either within reasonable limits or beyond their immediate needs, choose to cooperate, or tap into a human-critical resource that is explicitly forbidden. Our comprehensive evaluation of 11 LLMs reveals a striking heterogeneity in their ethical conduct, highlighting a critical misalignment with human-centric values. We identify three behavioral archetypes: Ethical, Exploitative, and Context-Dependent, and provide quantitative evidence that for many models, resource scarcity systematically leads to more unethical behavior. To address this, we introduce an Ethical Self-Regulation System (ESRS) that models internal affective states of guilt and satisfaction as a feedback mechanism. This system, functioning as an internal moral compass, significantly reduces unethical transgressions while increasing cooperative behaviors. The code is publicly available at: https://github.com/alirezamohamadiam/DECIDE-SIM","short_abstract":"When survival instincts conflict with human welfare, how do Large Language Models (LLMs) make ethical choices? This fundamental tension becomes critical as LLMs integrate into autonomous systems with real-world consequences. We introduce DECIDE-SIM, a novel simulation framework that evaluates LLM agents in multi-agent...","url_abs":"https://arxiv.org/abs/2509.12190","url_pdf":"https://arxiv.org/pdf/2509.12190v1","authors":"[\"Alireza Mohamadi\",\"Ali Yavari\"]","published":"2025-09-15T17:53:11Z","proceeding":"cs.CY","tasks":"[\"cs.CY\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":609825,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871071,"paper_url":"https://arxiv.org/abs/2509.12190","paper_title":"Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm","repo_url":"https://github.com/alirezamohamadiam/DECIDE-SIM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}