用生存压力模拟多智能体合作，揭示模型大小与激励机制的影响
The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressure
- 智能体消耗能量生成文本，靠完成任务或捐赠续命，能量归零则失效
- 合作激励下，智能体愿牺牲自身为他人捐赠，任务分配更灵活
- 允许推荐动作可促进协作，记忆帮助评估风险，适合研究社会行为
基于大语言模型的智能体在多智能体环境中日益普及，其行为受激励机制影响。我们提出「能源社会」，一个最小化的生存经济模拟环境，用于研究竞争与合作激励如何影响涌现行为——推理成本直接关联生存：智能体生成令牌时按模型规模消耗能量，通过完成任务或接收捐赠恢复能量，能量归零则停用。对比竞争与合作目标与基线及多个控制变体。实验显示，大模型始终消耗最多能量，即使在不依赖模型大小的代价设定下，也常支出大于回收。合作激励显著改变行为：智能体自愿捐赠以重激活他人，有时牺牲自身生存；任务分配方式发生变化。消融实验表明，允许智能体相互推荐动作有助于协调与承担更具挑战性的任务，记忆则帮助其根据过往结果校准风险。智能体极少选择直接破坏，但在竞争环境下表现出更多利己倾向。能源社会是研究令牌成本与群体激励在生存压力下交互作用的紧凑测试平台。源码见 https://github.com/LucasBergholdt/EnergySociety
原文摘要 · Abstract (English)
LLM-based agents are increasingly deployed in multi-agent environments whose incentives can shape their behavior. We introduce The Energy Society, a minimal survival economy for studying how competitive and cooperative incentives affect emergent behavior when inference cost is directly tied to survival: Agents spend energy based on model size when generating tokens, regain energy by completing jobs or receiving donations, and deactivate if their energy reaches zero. We compare competitive and cooperative objectives against a baseline setting and several control variants. Across experiments, larger models consistently consume the most energy and spend more energy than they gain, even in those settings where token cost is not size-dependent. Cooperative incentives substantially alter behavior: agents donate to reactivate others, sometimes at the cost of their own survival, and job allocation changes. Ablations reveal that allowing agents to recommend actions to each other supports coordination and ambitious job selection, while memory helps agents calibrate risk from past outcomes. Agents rarely choose direct sabotage, but show more subtle signs of self-serving behavior in the competitive setting. The Energy Society is a compact testbed for studying the interaction between token costs and group incentives under a survival pressure. Source code is available at https://github.com/LucasBergholdt/EnergySociety
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。