Lens methods inspect model computation by mapping intermediate activations to vocabulary tokens. Yet the concepts humans need to read out often span multiple tokens---entities, phrases, intermediate objects---making token-level readouts incomplete. Reliable multi-token readout with little model-specific preparation rem...
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
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.
