Work

Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents

Year: 2026

Type: conference-paper

Abstract: Deep research agents rely on iterative retrieval and reasoning to answer complex queries, but scaling test-time computation raises significant efficiency concerns.We study how to allocate reasoning budget in deep search pipelines, focusing on the role of listwise reranking.Using the BrowseComp-Plus benchmark, we analyze tradeoffs between model scale, reasoning effort, reranking depth, and total token cost via a novel effective token cost (ETC) metric.Our results show that reranking consistently improves retrieval and end-to-end accuracy, and that moderate reranking often yields larger gains than increasing search-time reasoning, achieving comparable accuracy at substantially lower cost.All our code is available at https://github.com/sahel-sh/DeepHone.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.1289

Authors: Sahel Sharifymoghaddam, Jimmy Lin

Institution: University of Waterloo

Language: English

Topic: Information Retrieval and Search Behavior

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Ministry of Science and ICT, South Korea, Natural Sciences and Engineering Research Council of Canada, Institute for Information and Communications Technology Promotion

Awards: G2759505043, G5704809196