collaborators

9 papers

cs.AI2026

Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions

Pengyu Zhu, Lijun Li, Longju Yang +2

Deep Research agents conduct long-horizon investigations by iteratively planning, retrieving evidence, and generating reports. However, it remains unclear whether they can resist a…

cs.AI2026

A Unified Framework for the Evaluation of LLM Agentic Capabilities

Pengyu Zhu, Lijun Li, Yaxing Lyu +8

As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores often jointly reflect model…

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

"LLM Agent Performance" Is Not a Single Evaluation Target

Pengyu Zhu, Li Sun, Philip S. Yu +1

LLM agent benchmark scores are shaped not only by the model but also by the agent harness, environment, evaluator, and inference budget. Unified execution controls these non-model…

cs.CL2026

STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics

Tingfeng Hui, Hao Xu, Pengyu Zhu +5

Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Exis…

cs.CL2025

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models

Ziqi Miao, Lijun Li, Yuan Xiong +3

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulne…