Traverse: Learning When to Remember, Reset, and Redirect for Long-Horizon Web Search
Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly difficult. We introduce an autonomous search harness in which the agent manages its own search process through three states: Rubric, Answer, and Verify. The agent firs...
Jing-Yuan Ma, L. Aster, He Zhang et al.
· 0 citations