Yuxuan Zhang
Reacherx
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement upvoted a paper 16 days ago
Dr. Claw: An AI Scientist Workspace for Vibe Research authored a paper 20 days ago
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?Organizations
Contribution: 60 structured tasks across web, OS, database, and embodied domains
#2 opened about 1 month ago
by Reacherx
Curated public collection for StructEval discovery
#2 opened about 2 months ago
by 
Reacherx
Curated external collection: Agentic Web & Computer-Use Benchmarks
#3 opened about 2 months ago
by Reacherx
Trace schema note: reproducing ClawBench V2 evaluations
#1 opened about 2 months ago
by Reacherx
Reproducing ClawBench V2 scores: corpus and evaluation protocol
#1 opened about 2 months ago
by Reacherx