用四条哲思原则让AI更理性自省，提升合作与适应力。
Contemplative Artificial Intelligence
- 基于禅修智慧设计四条原则：觉知、空性、无二、慈悲。
- 在AILuminate基准上性能提升显著（d=0.96），囚徒困境合作率大幅提高。
- 适合追求可信赖智能体的开发者，尤其关注长期安全与协作。
随着人工智能能力增强，传统对齐策略可能难以应对不可预测的自我改进、隐藏子目标以及系统复杂性。受冥想智慧传统的启发，我们提出通过四个公理化原则，在AI系统中构建稳健的「智慧世界模型」：第一，觉知（mindfulness）实现对涌现子目标的自我监控与校准；第二，空性（emptiness）避免目标固执，放松刚性先验；第三，无二（non-duality）消解主客对立边界；第四，无限关怀（boundless care）驱动普遍减缓痛苦。实验表明，引导AI反思这些原则可显著提升其在AILuminate基准的表现（d=0.96），并在囚徒困境任务中增强合作与联合奖励（d=7+）。文章提供了从架构、宪法到思维链强化的具体实现路径。未来，主动推理或可为具身智能体实现动态自组织的冥想式智能提供支持。
原文摘要 · Abstract (English)
As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of intelligent systems. Inspired by contemplative wisdom traditions, we show how four axiomatic principles can instil a resilient Wise World Model in AI systems. First, mindfulness enables self-monitoring and recalibration of emergent subgoals. Second, emptiness forestalls dogmatic goal fixation and relaxes rigid priors. Third, non-duality dissolves adversarial self-other boundaries. Fourth, boundless care motivates the universal reduction of suffering. We find that prompting AI to reflect on these principles improves performance on the AILuminate Benchmark (d=.96) and boosts cooperation and joint-reward on the Prisoner's Dilemma task (d=7+). We offer detailed implementation strategies at the level of architectures, constitutions, and reinforcement on chain-of-thought. For future systems, active inference may offer the self-organizing and dynamic coupling capabilities needed to enact Contemplative AI in embodied agents.
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。