Weihang Su
3 papers · Latest:
Natural Language Processing
Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
Judge-R1 enhances LLM-based judgment document generation through agentic legal information collection and rubric-guided optimization, improving accuracy.
2605.02011
Natural Language ProcessingDecoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation
This paper introduces Orthogonal Subspace Decomposition (OSD) to disentangle task and knowledge in PRAG, improving compositional robustness.
2604.26768
Natural Language ProcessingSkill Retrieval Augmentation for Agentic AI
This paper introduces Skill Retrieval Augmentation (SRA) for LLM agents, enabling dynamic skill retrieval from large corpora and presenting SRA-Bench for evaluation.
2604.24594
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.