#artificial intelligence
Jun 2026
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
Retrospective Harness Optimization is introduced, a self-supervised method that optimizes the agent harness using only past trajectories and alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.
Wenbo Pan, Shujie Liu, Chin-Yew Lin et al.
· arXiv.org · 8 citations
· ⚡1