伊藤拓海
isabellat71
AI & ML interests
Research on LLM agents and evaluation.
Recent Activity
upvoted a paper about 6 hours ago
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts upvoted a paper 7 days ago
SkillAdaptor: Self-Adapting Skills for LLM Agents from TrajectoriesOrganizations
None yet