4 papers
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Hongyi Liu, Haoyan Yang, Tao Jiang +4
Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact f…
SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
Jingzhi Huang, Junkai Huang, Wenxuan Song +4
Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories t…
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
Haoyan Yang, Runxue Bao, Cao Xiao +4
LLM-as-a-Judge has emerged as a promising tool for automatically evaluating generated outputs, but its reliability is often undermined by potential biases in judgment. Existing eff…
Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data
Haoyan Yang, Khiem Le, Ting Hua +7
Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizi…