1 citations · 3 across the 11 of their papers we have counts for
5 papers · 1 filter
LaVGuard: Selective Decoding for Contextual Value Drift
Jiale Dai, Liuxian Ma, Hongcan Deng +5
A content-safe response can still promote priorities that conflict with its task: an assistant may demand compliance when asked to preserve autonomy. We study contextual value drif…
ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification
Jieyun Huang, Yi Shen, Kaikai Zhao +7
Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-conscious classifiers in production systems. In Chinese SMS, attackers can exploi…
HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents
Jiangze Yan, Yi Shen, Wenjing Zhang +6
Long-horizon agents compress interaction histories into memory, but final outcomes entangle memory-writing credit with tool failures and reasoning errors. We propose HiMPO, a Hinds…
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-on…
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
Wenjing Zhang, Jiangze Yan, Jieyun Huang +7
Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection sampling. Standard methods treat t…