KunlunZhu

KunlunZhu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

upvoted a paper 7 days ago

CUADebug: Diagnosing and Repairing Computer-Use Agent Failures

commentedon a paper 3 months ago

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

View all activity

Organizations

commented a paper 3 months ago

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Paper • 2607.18754 • Published Jul 21 • 25 •

commented a paper about 1 year ago

Where LLM Agents Fail and How They can Learn From Failures

Paper • 2509.25370 • Published Sep 29, 2025 • 12 •

commented 2 papers over 1 year ago

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents

Paper • 2505.23559 • Published May 29, 2025 • 11 •

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

Paper • 2503.01935 • Published Mar 3, 2025 • 31 •