Skip to content
View reacher-z's full-sized avatar
39 followers · 141 following

Achievements

Achievement: Pull Sharkx3Achievement: Starstruckx3Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx3Achievement: Starstruckx3Achievement: Pair ExtraordinaireAchievement: YOLOAchievement: Quickdraw

Highlights

  • Pro

Block or report reacher-z

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
reacher-z/README.md

Hi, I'm Yuxuan Zhang

PhD student at University of British Columbia · Affiliated with Vector Institute · Research in AI Agents, LLMs, and RL

Website Research Program X Google Scholar

Research Program

I study how agentic AI can be evaluated, trained, and improved in realistic environments. My current work connects four research questions: real-world agent evaluation, inspectable self-improvement, efficient learning and information use, and evidence-grounded multimodal intelligence.

Explore the bilingual research map →

  Top Projects

ClawBench: Can AI Agents Complete Everyday Online Tasks? GitHub Stars

V1 preprint: 153 tasks across 144 live platforms · Current V2 project: 130 tasks across 63 platforms

Paper · Dashboard · Dataset · PyPI

VidGround: Watch Before You Answer GitHub Stars

Visually grounded post-training for video LLMs.

Paper · Project Page · HF Paper

Dr. Claw: Your AI Research Assistant GitHub Stars

A full-stack research workspace for taking projects from idea to paper.

Homepage · npm · Releases

OpenSkill: Open-World Self-Evolution for LLM Agents GitHub Stars

Builds both skills and verification signals from scratch, without target-task supervision.

Website · Paper · HF Paper

RewardHarness: Self-Evolving Agentic Post-Training GitHub Stars

COLM 2026 · A self-evolving agentic reward framework for image-editing evaluation.

Project Page · Paper · HF Paper · Releases

  GitHub Activity

GitHub Contribution Graph

  News

  Contact

 yuxuan.zhang(at)ubc.ca      Google Scholar      GitHub      X      Website

Pinned Loading

  1. TIGER-AI-Lab/ClawBench TIGER-AI-Lab/ClawBench Public

    Open-source benchmark for browser AI agents on daily tasks.

    Python 567 37

  2. vidground vidground Public

    Watch Before You Answer: Learning from Visually Grounded Post-Training (arXiv 2604.05117)

    Python 4

  3. HarnessBench HarnessBench Public

    Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.

    Python 40 2

  4. GraphEngineering GraphEngineering Public

    Vendor-neutral graph orchestration for reliable agentic systems: one portable Graph IR, native TypeScript/Python runtimes, deterministic barriers/routers, and cross-language conformance.

    TypeScript 4 1

  5. TIGER-AI-Lab/RewardHarness TIGER-AI-Lab/RewardHarness Public

    Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-model training. arXiv 2605.08703.

    Python 16 7