AINeutralarXiv – CS AI · 11h ago6/10
🧠
Revisiting Text Ranking in Deep Research
Researchers conducted a systematic analysis of text ranking methods in deep research tasks, examining how LLM-based agents retrieve and process web information. The study reveals that agent-generated queries follow web-search syntax favoring lexical and sparse retrievers, passage-level units outperform documents under context constraints, and a new query-translation method significantly improves retrieval effectiveness.