{"ID":23475245,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.20131","arxiv_id":"2609.20131","title":"Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking","abstract":"Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning trajectory, resulting in rankings that are susceptible to reasoning errors and inherently constrained in modeling the multifaceted signals underlying document relevance. To resolve this dilemma, we propose MERIT-Rank(Multi-perspective Evidence and Reasoning Integration for Text Reranking), a framework that models complementary reasoning trajectories to improve reranking robustness. MERIT-Rank formulates a Multi-Trajectory Reasoning Space (MTRS) that evaluates query-document relevance from multiple perspectives and introduces a joint reranker that consolidates these reasoning paths into a unified ranking decision. We further develop Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes reasoning trajectories while continually improving ranking quality through staged optimization objectives. Experiments on both reasoning-intensive and traditional retrieval benchmarks show that MERIT-Rank consistently achieves superior performance over competitive baselines. The 4B model notably outperforms most 7B and even 32B rerankers on BRIGHT.","short_abstract":"Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single reasoning trajectory, resulting in rankings that are susceptible to reasoning errors and inherently constrained in modeling the multifaceted signals under...","url_abs":"https://arxiv.org/abs/2609.20131","url_pdf":"https://arxiv.org/pdf/2609.20131v1","authors":"[\"Lijun Liu\",\"Zhengzong Chen\",\"Wenyan Li\",\"Yuanyuan Zhao\",\"Fei Huang\"]","published":"2026-09-17T12:24:24Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}