Loading activity…
@huaxiuyaoml
Assistant Professor @unccs @uncsdis | Postdoc @StanfordAILab | Author of RSI-Exam, MetaClaw, SkillRL, SimpleMem, AutoResearchClaw, Agent World Model, Agent0
AI
An October 25 post lists scores of 0.4943 and 0.5153, but the linked RSI-Exam leaderboard doesn't list Argon.
AI
Author Nathan Benaich cites an Anthropic index and argues robotics is nearing a “GPT-2 moment.”
XAI
A September 18, 2026 post puts Fable 5.1 at 0.4813 behind GPT-6-astra’s 0.5126, and says no model had yet reached the benchmark’s frontier-calibrated reference.
AI
Assistant professor highlights Alibaba Qwen model's score jump in recursive self-improvement benchmark.
AI
Assistant professor shares update on expanding the research skills benchmark and seeks new tasks.
