Supervising the search process produces reliable and generalizable information-seeking agents

Understand

Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search systems that iteratively interact with external knowledge sources.

• Despite this progress, building effective search agents remains challenging because high-quality intermediate search steps are difficult to generate.
• Previous approaches have primarily relied on outcome supervision, rewarding agents only for producing correct final answers.
• This often leads to reward hacking and excessive dependence on parametric memory, limiting generalization to out-of-domain tasks.