collaborators

7 papers

cs.LG2026

SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time

Qinfeng Li, Dalin He, Yuntai Bao +7

General-purpose skills promise reusable procedural knowledge for language agents, yet semantic relevance does not guarantee execution utility: a retrieved skill may encode assumpti…

cs.AI2026

AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction

Qinfeng Li, Yuntai Bao, Xinyan Yu +8

Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, co…

cs.LG2026

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

Yuntai Bao, Qinfeng Li, Xinyan Yu +6

Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effec…

cs.CR2026

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

Qinfeng Li, Yuntai Bao, Jianghui Hu +5

LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments,…

cs.LG2026

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

Yuntai Bao, Xuhong Zhang, Jintao Chen +7

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tun…

cs.CL2026

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization

Yuntai Bao, Xuhong Zhang, Tianyu Du +4

Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the pred…