AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs

Sheshansh Agrawal, Thien Hang Nguyen, Douwe Kiela

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use greedy SCC scheduling instead of random candidate subsets (ablation)BlitzRank · Synthetic transitive n=100,k=10oracle calls: 132.1 -> 37.7Improved
use greedy SCC scheduling instead of random subsets from all nodes (ablation)BlitzRank · Synthetic transitive n=200,k=10oracle calls: 2554.6 -> 89.2Improved
use greedy SCC scheduling instead of random candidates (ablation)BlitzRank · Synthetic transitive n=200,k=20oracle calls: 129.4 -> 33.8Improved
reduce window size from 20 to 10Sliding Window · TREC DL19 (GPT-4.1)nDCG@10: 74.0 -> 56.4Hurt
reduce window size from 20 to 10BlitzRank · TREC DL19 (GPT-4.1)nDCG@10: 74.6 -> 73.6No clear effect
reduce window size from 20 to 10BlitzRank · TREC DL20 (GPT-4.1)nDCG@10: 70.7 -> 72.4No clear effect
use BlitzRank k10 instead of k20BlitzRank · 14 datasets x 5 LLMs avgnDCG@10: 56.0 -> 56.5Improved
use BlitzRank k10 instead of k20BlitzRank · Qwen3-235BnDCG@10: 54.7 -> 55.6Improved
use BlitzRank k10 instead of pairwise rerankingLLM reranking · 14 datasets (GPT-4.1 & Gemini-3-Flash)tokens per query: 324k -> 42kImproved
use BlitzRank k10 instead of Sliding WindowLLM reranking · 14 datasets (GPT-4.1 & Gemini-3-Flash)tokens per query: 54k -> 42kImproved
use BlitzRank k10 instead of AcuRankLLM reranking · 14 datasets (GPT-4.1 & Gemini-3-Flash)tokens per query: 69k -> 42kImproved
double compute with repeated runs (R2 variant)SW · 14 datasets (GPT-4.1 & Gemini-3-Flash)nDCG@10: 56.7 -> 56.5No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy