让语言模型做出更稳健的决策，通过不确定性建模避免盲目依赖单一数值。
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
- 用带不确定性的命题图表示问题，融合结构先验与假设溯源
- 在41,188条真实决策上，回测表现优于现状34%，减少优化器诅咒
- 提供可审计的决策追溯和后悔值边界，适合高风险决策场景
语言模型将自然语言情境转化为数值计划，现有主流方法（NL4Opt、OptiMUS、ORLM、OR-LLM-Agent）通常固定单一目标并采用点估计系数，仅求解一次。但涉及真实预算、资源或临床关注的决策中，这种确定性假设极易失效：每个数值都是潜在假设，仅在假设完全正确时最优的方案本质上脆弱且类比计算。YUKTI 改变了自动形式化的目标，其表示为带有类型命题的图结构，关系携带形状先验、系数不确定性及来源信息。该框架在各阶段使用精确、非线性或进化求解器；通过分布式帕累托传递耦合阶段；引入假设鲁棒帕累托前沿（ARPF），对假设（包括结构性epsilon污染）进行重采样，评估每项行动的存活频率（rho）。我们证明了rho是决策后悔的精确因子，并增强了可审计追溯性；在无基准数据时构建了符合实际的测试数据集（SRJANA）。验证表明：在受控误设下，鲁棒妥协方案使均值与尾部后悔降低超90%；在受监管商业决策中，优化在合法空间内进行并以欧元量化下行风险；在包含41,188条真实决策的公共数据集上，样本外回测优于现有做法34%，优于朴素点规则4%，同时缓解优化器诅咒。求解器为标准工具，不宣称基准领先。对比实验显示，即使给定正确数值并单目标优化，大模型仍产生约47倍于YUKTI的持有期后悔——大模型是形式化者，而非求解者。当存在长程因果耦合时，前向传递失效，需转为后向归纳因果策略。
原文摘要 · Abstract (English)
Language models turn a worded situation into a numeric plan, and the dominant pipelines (NL4Opt, OptiMUS, ORLM, OR-LLM-Agent) commit to a single objective and point-valued coefficients, then solve once. For decisions that allocate real budget, effort, or clinical attention, that confidence is the failure mode: every objectified number is an assumption, and a plan optimal only if the guesses are exactly right is fragile -- mimicry of computation. YUKTI changes the target of autoformulation. Its representation is a typed-proposition graph whose relationships carry shape priors, coefficient uncertainty, and provenance. YUKTI routes each stage to an exact, nonlinear, or evolutionary solver; couples stages by a distributional Pareto hand-off; and introduces Assumption-Robust Pareto Frontiers (ARPF), resampling assumptions (including structural epsilon-contamination) to score how often each action survives (rho). We prove a bound making rho an exact factor of decision regret, add auditable traceability, and synthesize a benchmark-faithful data foundation when none exists (SRJANA). We validate three ways: under controlled misspecification the robust compromise cuts mean and tail regret by over 90% versus a naive point plan; on a regulated commercial decision we optimize inside a lawful action space and price the downside in euros; and on a real public dataset of 41,188 decisions an out-of-sample backtest beats the logged status quo by 34% and a naive point rule by 4% while reducing the optimizer's curse. The solvers are standard; we claim no benchmark-SOTA win. A head-to-head shows an LLM given the correct numbers, and single-objective optimization, both incur about 47x the held-out regret of YUKTI -- an LLM is a formulator, not a solver. Under long-range causal coupling, the forward hand-off becomes unsound, locating where it must become a backward-induction causal policy.
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。