SOURCE-LINKED INTELLIGENCE

CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Reliable search requires more than acquiring external evidence. An agent must also recognize and recover from errors as its trajectory unfolds. In-trajectory feedback provides a mechanism for such recovery by diagnosing where the search has drifted and redirecting subsequent reasoning steps. This is particularly important in long-horizon search, where an early directional error may receive no immediate corrective signal and can compound across later steps. Making such feedback learnable, however, creates a coupled problem: the agent must learn when to request and use feedback, while the critic

Read original source ↗ Open in workspace

recordType

paper

region

Global