S²-MAS 发布：5 亿家庭智能体的大规模社会模拟框架
S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents
有人用 5 亿个模拟家庭做经济实验，小模型成绩还压过 GPT-6-Luna，做经济或政策模拟的可以看看这篇。
S²-MAS 是一个基于真实调查数据构建的社会级多智能体模拟框架，包含 5 亿合成家庭 persona。其 Genese 引擎将决策与状态更新分离，通过金融场景和应用账本追踪消费、现金、债务与还款。底层模型 sharp-421m-mlx 用 293 万样本做 SFT + RLCD 训练，在一次性消费金融选择题上达到 74.55% 准确率和 38.37% 的 question-macro F1，超过 GLM-5.3-Flash、DeepSeek-V4.1-Flash、GPT-6-Luna 等模型。团队用 1200 万个不同家庭智能体做了购买融资对照实验，发现同时提高购买目标与授信额度会提升消费，且不同年龄和收入群体的反应存在差异。
S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents
Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic household personas grounded in real-survey data. Its Genese engine separates decisions from state updates, while reusable financial scenarios and application ledgers track consumption, cash, debt and payments. Trained with SFT + RLCD on 2.93 million examples, sharp-421m-mlx achieves 74.55% accuracy and 38.37% question-macro F1 on one-shot consumer financial-choice tasks derived from held-out survey responses. Its accuracy exceeds GLM-5.3-Flash, Jev 1.13, DeepSeek-V4.1-Flash, GPT-6-Luna and GPT-6-Astra in the common benchmark (full test for the first four; matched 500-group sample for Astra). We evaluate eight financial task families and simulate 12 million distinct household agents in paired purchase-funding conditions. Jointly raising purchase goals and approved credit limits increases consumption, with responses differing across age and income groups. Education, employment and household-size differences persist after age-income standardization and mainly reflect transitions from deferral to purchase. Asset and debt groups differ in cash drawdown, repayment and closing debt. A response-stratified 24-month panel varies purchase goals under a common credit product, with repayment and arrears updating subsequent offers. S$^2$-MAS links heterogeneous household decisions to evolving consumption, cash and repayment paths, supporting economic experiments across household groups, population scales and time horizons.
