Log inSign up
Zae Myung Kim profile banner
user avatar

Zae Myung Kim

@zaemyung
zaemyung.github.io
Joined February 2022
57
Following
41
Followers
RepliesMedia
  • Pinned
    user avatar
    Zae Myung Kim
    @zaemyung
    Apr 16
    🏁 New paper: The Amazing Agent Race We tested whether LLM agents can navigate Wikipedia, call tools, and compute answers across multi-step scavenger-hunt puzzles. Key finding: agents are strong tool users but terrible navigators with 37% overall accuracy. Here's why they fail
    Image
    Image
  • user avatar
    Zae Myung Kim
    @zaemyung
    Apr 30, 2025
    🚨 New Paper Alert! 🚨 How can we align language models without drowning in prompt engineering or falling into reward hacking traps? We introduce Meta Policy Optimization (MPO)—a new reinforcement learning framework that evolves its own reward model rubrics through meta-level
    Image
    Image
    Image
  • user avatar
    Zae Myung Kim
    @zaemyung
    Feb 19, 2024
    "Paraphrasing attacks" can compromise the effectiveness of AI content detectors. 🙀 Can hierarchical structures in texts help build a more robust detector? Our research reveals a resounding💡YES!💡Delighted to share our work on merging discourse frameworks with graph analysis.
    Image