5 papers
SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
Yu Cheng, Yongkang Hu, Shuaijie Ma +12
LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available only after each task is comple…
Memory Intelligence Agent
Jingyang Qiao, Weicheng Meng, Yu Cheng +6
Deep research agents (DRAs) integrate LLM reasoning with external tools. Memory systems enable DRAs to leverage historical experiences, which are essential for efficient reasoning…
Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework
Jingyang Qiao, Zhizhong Zhang, Xin Tan +3
Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibitin…
Large Continual Instruction Assistant
Jingyang Qiao, Zhizhong Zhang, Xin Tan +3
Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily d…
Gradient Projection For Continual Parameter-Efficient Tuning
Jingyang Qiao, Zhizhong Zhang, Xin Tan +4
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common probl…