LoyalAgent-Bench is introduced, comprising 10,298 samples across 42 subscenarios and six domains, and an online GRPO framework that trains against a LLM opponent to generate mechanism-specific reward signals, formalizing Agent Loyalty as an information-control property requiring agents to prevent Exploitable Informatio...
Zi-Meng Huang, Shi-Lei Chen, Jia-Tong Zhao et al.· 1 citation
Across three model families, two small groups of attention heads are identified with distinct roles in introspective reporting supporting introspective detection and localization of large language models.
Jia-Hong Zou, Xiang-Kun Sun, Ling-Kai Kong et al.· 0 citations
Experiments across diverse upstream models show that PILA consistently improves ad effectiveness while preserving response quality, highlighting its promise as a practical solution for LLM-native advertising.
GraceKV is proposed, a global approach for the allocation of resolution and coverage in KV cache compression, and the compression process is formulated as a global resource allocation problem under a fixed cache budget to validate the effectiveness of global budget allocation in coordinating information coverage and lo...
This work constructs the missing supervision through a psychologically grounded agent simulation framework, and distil it into a parameter-efficient evaluator that predicts click-through intent, together with the three companion dimensions of ad quality, as smooth, differentiable estimates.
John L. Turner-Smith, Zimeng Huang, Yuhan Fu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
