InvSTG-PLM, an invariance-aware spatiotemporal graph learning framework that grounds PLMs in invariant structures, is proposed and a deterministic robustness bound is justified, showing that mean–variance control upper bounds worst-case risk over simulated environments.
Ting Wang, Duo Zhou, Daqian Shi et al.· Proceedings of the 32nd ACM...· 0 citations
This survey synthesizes agentic reasoning methods into a unified roadmap bridging thought and action, and outlines open challenges and future directions, including personalization, long-horizon interaction, world modeling, scalable multi-agent training, and governance for real-world deployment.
Tian-Xin Wei, Ting-Wei Li, Zhining Liu et al.· 39 citations· ⚡6
The results reveal a pattern distinct from prior findings on long-tail vulnerability during acquisition and retention: among facts that models already answer correctly, those associated with highly connected entities are more likely to be corrupted by neighboring updates, and updates to such facts propagate errors more...
Yu-Ji Zhang, Wei-Bing Wang, Cheng Qian et al.· 0 citations
This work presents a general recipe to integrate lookahead into any branch-and-bound verifier and demonstrates how one of the current state-of-the-art branching heuristics, FSB, can be viewed as a special instantiation of the lookahead branching strategy.
Liam Davis, Duo Zhou, Huan Zhang et al.· Proceedings of the Thirty-Fi...· 1 citation
AdaFuse is an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation that establishes a synergistic interaction between adaptive ensembling and test-time scaling, where ensemble decisions guide targeted exploration, and the resulting diversity in turn stren...
