Tag
This paper introduces neural slack variables, a primal-side approach that converts constraint enforcement into a regression problem by coupling the primary network with a jointly learned auxiliary network, achieving zero violations on monotonicity and convexity tests and enabling arbitrage-free learning of volatility surfaces.
SDOF is a framework that treats multi-agent execution as a constrained state machine, using an online-RLHF specialized intent router and state-aware dispatcher to enforce business process stage constraints, achieving 86.5% task completion on a recruitment system with 6,000+ enterprises.
This research paper introduces adaptive correction scheduling for enforcing hard constraints in generative sampling, demonstrating that it improves the cost-accuracy frontier compared to terminal or stepwise projection methods.