Patcher is a novel and efficient adversarial training algorithm that alternates between an attack stage and a defense stage: the attack stage simulates many-step malicious finetuning and computes the resulting parameter displacement as an"attack vector", while the defense stage aims to preserve safe behavior under such...
Hao-Min Wen, Shi Chen, Qingyu Shi et al.· arXiv.org· 0 citations
This work compares the student view and training fixed within each scale against three abstractions compiled offline, a named strategy, a method-independent framing, and a problem category, and against an answer-only control that keeps the destination but removes the path.
Kang-Hui Tian, Si-Yuan Liu, Tianxiang Jiang et al.· 2 citations
A*-Thought-V2 is presented, a geometric dynamics of LLM guided framework that models CoT as a hidden-state trajectory and replaces hard deletion with an explicit-implicit interleaved latent architecture that reflects broader soft targets that encourage richer step-level feature learning.
Xiao-An Xu, Si-Yuan Liu, Shuo Wang et al.· 1 citation
This work introduces EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games, and evaluates memory agents with strong LMs/VLMs as backbones, using in-context prompting as baselines.
Xinze Li, Zi-Yue Zhu, Siyuan Liu et al.· arXiv.org· 7 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
