AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval

Haike Xu, Tong Chen

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons · 3 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
replace sequential reranking with reranker-guided graph search (RGS)Retrieve-and-Rerank, Reranker@100 · BRIGHTNDCG@10: 25.3 -> 28.8Improved
replace sequential reranking with RGSRetrieve-and-Rerank, Reranker@500 · BRIGHTNDCG@10: 27.7 -> 33.0Improved
replace sequential reranking with RGSRetrieve-and-Rerank, Reranker@100 · FollowIRNDCG@10: 60.4 -> 63.3Improved
replace sequential reranking with RGSRetrieve-and-Rerank, Reranker@500 · FollowIRNDCG@10: 61.6 -> 64.2Improved
replace sequential reranking with RGSRetrieve-and-Rerank, Reranker@100 · M-BEIRNDCG@10: 25.9 -> 31.0Improved
replace sequential reranking with RGSRetrieve-and-Rerank, Reranker@500 · M-BEIRNDCG@10: 30.1 -> 38.3Improved
use RGS instead of SlideGARSlideGAR, Reranker@500 · BRIGHTNDCG@10: 26.9 -> 33.0Improved
use RGS instead of sequential reranking on math/codeRetrieve-and-Rerank · BRIGHT AoPS and LeetCodeNDCG@10: 25.8 -> 22.1No clear effect
increase reranker budget from 100 to 500SlideGAR · FollowIRNDCG@10: 62.5 -> 59.8Hurt
increase reranker budget from 100 to 500RGS · BRIGHTNDCG@10: 28.8 -> 33.0Improved
start RGS from noisy start point or default ANNS start instead of exact closest document (ablation)RGS · BRIGHTNDCG@10No clear effect
run RGS on KNN graph instead of DiskANN graph (ablation)RGS · BRIGHTNDCG@10Hurt

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