Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such large-scale harm requires jointly modeling informational and financial dynamics. Yet existing simulators typically capture only one side of this intera...
Ke-Yang Chen, Ming-Xuan Jiang, Ze-Ping Li et al.· 0 citations
An action seen once and the same action seen three times receive the same action-recognition label, so that supervision does not require a model to count. Answers shared across histories that differ in event order, accumulation, or relations leave those distinctions unconstrained; we call this state under-specification...
Yihao Hu, Pan Wang, Yi-Tong Lin et al.· 0 citations
Objective-wise Reconciled Policy Gradient (ORPG), which constructs a separate clipped policy objective for each reward and reconciles the resulting gradients into one policy update, achieves the highest average full-budget accuracy and three-budget hypervolume among the compared methods.
Next-turn user reactions provide actionable local credit for improving multi-turn user-interacting agents and improves the nine-domain $\tau$-family average across three independently trained runs.
Yi-Wen Zhao, Zhihao Wen, Yuchen Mao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.