6 papers · 1 filter
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
Yaxing Lyu, Shengjie Zhou, Binbin Toh +2
As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before taking actions. We introduce KC-B…
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…
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
Yuan Xiong, Linji Hao, Shizhu He +3
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…
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
Yuan Xiong, Ziqi Miao, Qian Chen +6
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…
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…
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…