3 papers
cs.CR2026
Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agents
Haochang Hao, Dehai Min, Zhifang Zhang +4
Agent skills extend general-purpose agents, but their open format enables skill poisoning: a tampered skill can make an agent run an attacker's command while completing the user's…
cs.CL2026
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +3
Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supe…
cs.CL2026
SafeCRS: Personalized Safety Alignment for LLM-Based Conversational Recommender Systems
Haochang Hao, Yifan Xu, Xinzhuo Li +2
Current LLM-based conversational recommender systems (CRS) primarily optimize recommendation accuracy and user satisfaction. We identify an underexplored vulnerability in which rec…