Abstract
Language models transform worded situations into numerical plans, but dominant pipelines (NL4Opt, OptiMUS, ORLM, OR-LLM-Agent) typically focus on a single objective with point-valued coefficients, solving once. For decisions allocating real budgets, effort, or clinical attention, this confidence becomes a failure mode: every objectified number is an assumption, and a plan optimal only if guesses are exact is fragile—a mimicry of computation.
YUKTI shifts the target of autoformulation. Its representation is a typed-proposition graph whose relationships bear shape priors, coefficient uncertainty, and provenance. YUKTI routes each stage to an exact, nonlinear, or evolutionary solver; couples stages via 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 in 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 within 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.
Blogger's Review: YUKTI's innovation lies in its introduction of Assumption-Robust Pareto Frontiers, significantly enhancing decision reliability. Compared to traditional single-objective optimization, YUKTI better handles uncertainty, providing more robust solutions for complex decisions, especially in budgeting and resource allocation. Its comparative analysis clearly highlights the limitations of conventional methods, making it a noteworthy development.