AI RESEARCH
BLITZRANK: Principled Zero-shot Ranking Agents with Tournament Graphs
arXiv CS.LG
•
ArXi:2602.05448v3 Announce Type: replace Selecting the top $m$ from $n$ items via expensive $k$-wise comparisons is central to settings ranging from LLM-based document reranking to crowdsourced evaluation and tournament design. Existing methods either rely on heuristics that fail to fully exploit the information each comparison reveals, or are inefficient when they do. We