Jingbo Shang | Xunyi's Academic Websitehttps://jiangxunyi.github.io/authors/jingbo-shang/Jingbo ShangHugo Blox Builder (https://hugoblox.com)en-usMon, 20 Jul 2026 00:00:00 +0000https://jiangxunyi.github.io/media/icon_hu12864870738162112581.pngJingbo Shanghttps://jiangxunyi.github.io/authors/jingbo-shang/RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rolloutshttps://jiangxunyi.github.io/publication/rrpo/Mon, 20 Jul 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/rrpo/<p>RRPO extends group-relative reinforcement learning to tasks without a direct correctness verifier. It compares candidate rollouts against positive and negative reference sets to construct training advantages for reasoning and open-ended generation.</p>Skill-R1: Agent Skill Evolution via Reinforcement Learninghttps://jiangxunyi.github.io/publication/skillr1/Sun, 10 May 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/skillr1/<p>Skill-R1 trains a small generator to improve reusable natural-language procedures while keeping the task model fixed. Feedback from successive rollouts guides skill revisions, enabling adaptation with both open and closed models.</p>Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learninghttps://jiangxunyi.github.io/publication/rolloutsurvey/Wed, 08 Apr 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/rolloutsurvey/<p>This survey organizes rollout design for language-model reinforcement learning into generation, filtering, control, and replay. It connects design choices to reliability, coverage, and computational cost, with examples across reasoning and agent tasks.</p>