3 papers
cs.CL2026
MoE-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation
Qingyu Yang, Haonan He, Minglei Li +4
Mixture-of-Experts (MoE) architectures have been widely adopted in large language models, yet parameter-efficient fine-tuning (PEFT) for MoE models remains underexplored. Existing…
cs.CL2026
From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
Bo Tang, Yang Zhang, Guomian Zhuang +8
Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propo…
cs.CL2026
Parametric Skills
Xuan Zhao, Haonan He, Qingyu Yang +5
Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually authored or extracted…