collaborators

8 papers

cs.AI2026

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

Xinshun Feng, Ziqi Miao, Lijun Li +1

Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such se…

cs.AI2026

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety

Yuan Xiong, Linji Hao, Shizhu He +2

Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizo…

cs.AI2026

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents

Yuan Xiong, Ziqi Miao, Qian Chen +5

Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumul…

cs.AI2026

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

Hao Li, Jingkun An, Zijun Song +8

Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual object…

cs.AI2026

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

Ziqi Miao, Haonan Jia, Lijun Li +4

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR appr…

cs.LG2026

Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation

Zihang Xu, Haozhi Xie, Ziqi Miao +3

Large reasoning models (LRMs) achieve strong performance through extended reasoning traces, but they often exhibit overthinking behavior for low-complexity queries. Existing effort…