Zihan Huang | Xunyi's Academic Websitehttps://jiangxunyi.github.io/authors/zihan-huang/Zihan HuangHugo Blox Builder (https://hugoblox.com)en-usTue, 01 Sep 2026 00:00:00 +0000https://jiangxunyi.github.io/media/icon_hu12864870738162112581.pngZihan Huanghttps://jiangxunyi.github.io/authors/zihan-huang/Reasoning Pathologies in Large Language Models: A Diagnostic Perspectivehttps://jiangxunyi.github.io/publication/reasoningpathologies/Tue, 01 Sep 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/reasoningpathologies/<p>A diagnostic study of reasoning failures in large language models.</p>The Geometry of Agent Skills: Non-Commutative Composition in Representation Spacehttps://jiangxunyi.github.io/publication/agentskillgeometry/Tue, 01 Sep 2026 00:00:00 +0000https://jiangxunyi.github.io/publication/agentskillgeometry/<p>A study of the geometry of agent skills and how their composition depends on order in representation space.</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>