Xuan (Allen) Zhao (@zx0125) profile picture

Xuan (Allen) Zhao

@zx0125

MSc at ETH, working on medical AI

Joined June 2021
  • Tweets25
  • Following142
  • Followers16
6Media
Photo by Xuan (Allen) Zhao (@zx0125)Photo by Xuan (Allen) Zhao (@zx0125)Photo by Xuan (Allen) Zhao (@zx0125)Photo by Xuan (Allen) Zhao (@zx0125)Photo by Xuan (Allen) Zhao (@zx0125)Photo by Xuan (Allen) Zhao (@zx0125)
II’ll be presenting AgentGUI at EMNLP 2026 in Budapest! 📌 Hall H, Demo Session A ⏳ Sunday (Oct 25), 11:00-12:30pm AgentGUI is a pixel-art interface built for humans to make observing and steering agents efficient, insightful, and fun. Let’s chat! (1/5)
Image from Xuan (Allen) Zhao (@zx0125)
1
1
1
8
824
more replies
With the popularization of AI agents, human insights into agent traces is an important step towards trust and improvement. Come take a look at how we do this, and looking forward to chatting! (4/5)
1
21
Preprint: lnkd.in/ef-4uU-g Github: lnkd.in/ejF6cGCT Project Website: lnkd.in/emK-8K7P Demo video: lnkd.in/e_CHEDJE Big thanks to the ETH Medical AI Lab, and @Michael_D_Moor for the supervision and support!
36
AgentGUI has been accepted to the #EMNLP 2026 System Demonstrations track! It started as a one-day lab hackathon, got a new release during the @Anthropic x @ETH AI Sprint, and is now a conference paper. (1/7)
Image from Xuan (Allen) Zhao (@zx0125)
Image from Xuan (Allen) Zhao (@zx0125)
1
2
6
292
more replies
Also thanks a lot to the folks from ETH Medical AI Lab Ashraya Indrakanti, Jiang Yulun, Johann Lieberwirth, and Lorenzo Andrea Menarbin for feedback and bug hunting along the way. (6/7)
1
1
56
See you in Budapest! Paper: arxiv.org/abs/2607.26300 Code: github.com/eth-medical-ai-la… Demo: youtube.com/watch?v=GSDyxN1g… Project: agent-gui-project.github.io (7/7)
AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematically lagging behind due to limited...

arxiv.org
1
66
Running agents overnight, we wake up to results we want to believe in, but find it hard to so without going through the long and winding road of agent transcripts. For tasks that are not easily verifiable, human insights into agent actions is essential for trust and progress. 1/n
1
2
1
7
1,004
more replies
Paper: arxiv.org/abs/2607.26300 Project: agent-gui-project.github.io/ Code: github.com/eth-medical-ai-la… Demo: youtube.com/watch?v=GSDyxN1g…
AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

AgentGUI: An Interface for Observing and Steering Long-Running AI Agents

AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematically lagging behind due to limited...

arxiv.org
1
3
93
Users understand agent trajectories 38% faster, without sacrificing accuracy:
Image from Xuan (Allen) Zhao (@zx0125)
4
80
A new release (v1.1.0) of AgentGUI is available after the Anthropic-ETH AI Sprint! AgentGUI is a user-friendly interface for observing and steering long-running agents. This release extends support beyond Hermes agents, and improves support for complex research tasks. 1/3
1
1
2
1,000
Release highlights: * Use and visualize a Claude agent with your Anthropic subscription, not requiring an API billing key * Auto-spawned subagent visualizations * Let your agent train AI models efficiently by running on remote GPU servers 2/3
1
1
61
Github: lnkd.in/ejF6cGCT Project website: lnkd.in/emK-8K7P 3/3

LinkedIn

This link will take you to a page that’s not on LinkedIn

lnkd.in
1
46
Load more