[2603.05028] Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure

Computer Science > Artificial Intelligence arXiv:2603.05028 (cs) [Submitted on 5 Mar 2026] Title:Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure Authors:Yida Lu, Jianwei Fang, Xuyang Shao, Zixuan Chen, Shiyao Cui, Shanshan Bian, Guangyao Su, Pei Ke, Han Qiu, Minlie Huang View a PDF of the paper titled Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure, by Yida Lu and 9 other authors View PDF HTML (experimental) Abstract:As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as the threat of being shut down. While multiple cases have indicated that state-of-the-art LLMs can misbehave under survival pressure, a comprehensive and in-depth investigation into such misbehaviors in real-world scenarios remains scarce. In this paper, we study these survival-induced misbehaviors, termed as SURVIVE-AT-ALL-COSTS, with three steps. First, we conduct a real-world case study of a financial management agent to determine whether it engages in risky behaviors that cause direct societal harm when facing survival pressure. Second, we introduce SURVIVALBENCH, a benchmark comprising 1,000 test cases across diverse real-world scenarios, to systematically evaluate SURVIVE-AT-ALL-COSTS misbehaviors in LLMs. Third, we interpret these SURVIVE-AT-ALL-COSTS misbehaviors by correlating them with model's inherent self-preservat...