SocialMaze is introduced, a benchmark that organizes six tasks across social deduction games, daily-life interactions, and digital community platforms along three descriptive design axes: deep reasoning, dynamic interaction, and information uncertainty.
Zi-Xiang Xu, Yan-Bo Wang, Yue Huang et al.· 1 citation
A benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth is introduced, establishing scalable geometric reasoning as an open challenge for vision-language models.
DOG-DPO is proposed, a training-free data selection framework that treats preference pairs as structured geometric signals and recovers most of the safety gains of full-data training while remaining entirely teacher-free, training-free, and substantially faster than representative selection baselines.
Yi Nian, Tiankai Yang, Yudi Zhang et al.· arXiv.org· 1 citation
WeClawArena is introduced, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.
P. Wang, Ao-Jie Yuan, Haiyu Zhang et al.· 1 citation
CatchBench puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST), which none scores all three under one task-method interface.
Yue Zhao, Meng-Yuan Li, Ruo-Lin Li et al.· 4 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.