3 papers
cs.AI2026
Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
Zhongan Bi, Kepeng Lin, Xuanang Gao +2
Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on…
cs.LG2026
Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning
Zijun Weng, Zhongan Bi, Xuanang Gao +5
Reinforcement learning (RL) changes not only what language models say, but also how much they say, often increasing response length at the cost of token efficiency. Controlling thi…
cs.CR2026
Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
Zhongan Bi, Qiwen Wang, Jianrong Jiang +11
Search-augmented LLM agents are increasingly used for consumer decisions, making them vulnerable to Generative Engine Optimization (GEO) poisoning. Existing benchmarks largely meas…