资源理性契约主义应指导AI对齐
Resource Rational Contractualism Should Guide AI Alignment
AI总结：
本文提出资源理性契约主义框架，通过认知启发式方法提升AI决策效率与适应性，解决大规模契约达成成本高问题。
摘要：
AI系统将需在人类环境中运作并做出影响人类及其他AI代理的决策，其目标和价值观可能不一致。契约主义对齐主张基于多方在合适条件下会同意的协议来指导决策，但大规模达成此类协议仍成本高且缓慢，即使对于先进AI也是如此。因此，本文提出资源理性契约主义（RRC）：一种框架，使AI系统通过一组规范性基础、认知启发式的工具，以换取准确性的代价来近似理性当事人会形成的协议。一个RRC对齐的代理不仅会高效运作，还能够动态适应和解读不断变化的人类社会世界。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
