collaborators

21 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

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

Chunxiao Li, Yuan Xiong, Lijun Li +4

Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely…

cs.CL2026

An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

Zhida He, Xia Hu, Baichen Le +20

Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the…

cs.CL2026

Evolutionary Guided Decoding: Iterative Value Refinement for LLMs

Zhenhua Liu, Lijun Li, Ruizhe Chen +5

While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effective…

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.CR2026

HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment

Yuexiao Liu, Lijun Li, Xingjun Wang +1

Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have gained significant attention due to their objective and verifiable reward signals, demonstrating s…