zhan

zzsamshi

3

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 29 days ago

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

upvoted a paper about 1 month ago

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

upvoted a paper 5 months ago

Position: Agentic Evolution is the Path to Evolving LLMs

View all activity

Organizations

None yet

zzsamshi 's models

None public yet