FORT-Searcher: Shortcut-Resistant Training Data Framework for Deep Search Agents
Identifies four concrete shortcut risks in existing deep-search training data — evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding — that let agents bypass genuine multi-hop search. FORT synthesizes shortcut-resistant data by controlling these risks across entity selection, evidence graph construction, and question formulation. FORT-Searcher achieves state-of-the-art among open-source search agents of comparable size.
Why it matters
Deep search agents are increasingly important, but training-data quality has been poorly understood. FORT is the first principled shortcut-aware difficulty framework. #4 on HF Daily June 12 with 44 upvotes.
Importance: 2/5
#4 HF Daily June 12 (44 upvotes), addresses fundamental training data quality issue for search agents