用资源理性框架让AI高效达成人类共识，适应复杂社会环境。
Resource Rational Contractualism Should Guide AI Alignment
- 用认知启发式工具箱权衡努力与准确度，近似理性共识
- 在高成本共识场景下实现快速决策，效率提升显著
- 适合需要动态适应社会规则的AI系统开发者
AI系统将很快需在人类环境中决策，影响多方利益，而目标与价值观各异。传统契约主义对齐依赖广泛协商，但代价高昂且缓慢，即使对先进AI也如此。为此我们提出资源理性契约主义（RRC）：一种框架，使AI通过一系列规范性驱动、类人启发式策略，在努力与准确性间权衡，近似理性主体在理想条件下会达成的协议。一个经RRC对齐的代理不仅运行高效，还能动态适应并理解不断变化的人类社会世界。
原文摘要 · Abstract (English)
AI systems will soon have to navigate human environments and make decisions that affect people and other AI agents whose goals and values diverge. Contractualist alignment proposes grounding those decisions in agreements that diverse stakeholders would endorse under the right conditions, yet securing such agreement at scale remains costly and slow -- even for advanced AI. We therefore propose Resource-Rational Contractualism (RRC): a framework where AI systems approximate the agreements rational parties would form by drawing on a toolbox of normatively-grounded, cognitively-inspired heuristics that trade effort for accuracy. An RRC-aligned agent would not only operate efficiently, but also be equipped to dynamically adapt to and interpret the ever-changing human social world.
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。