Saved in:
Bibliographic Details
Main Author: Hsu, Jerome Tze-Hou
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.04402
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917315092676608
author Hsu, Jerome Tze-Hou
author_facet Hsu, Jerome Tze-Hou
contents The rapid growth of Retrieval-Augmented Generation (RAG) has created a proliferation of toolkits, yet a fundamental gap remains between experimental prototypes and robust, production-ready systems. We present SearchGym, a modular infrastructure designed for cross-platform benchmarking and hybrid search orchestration. Unlike existing model-centric frameworks, SearchGym decouples data representation, embedding strategies, and retrieval logic into stateful abstractions: Dataset, VectorSet, and App. This separation enables a Compositional Config Algebra, allowing designers to synthesize entire systems from hierarchical configurations while ensuring perfect reproducibility. Moreover, we analyze the "Top-$k$ Cognizance" in hybrid retrieval pipelines, demonstrating that the optimal sequence of semantic ranking and structured filtering is highly dependent on filter strength. Evaluated on the LitSearch expert-annotated benchmark, SearchGym achieves a 70% Top-100 retrieval rate. SearchGym reveals a design tension between generalizability and optimizability, presenting the potential where engineering optimization may serve as a tool for uncovering the causal mechanisms inherent in information retrieval across heterogeneous domains. An open-source implementation of SearchGym is available at: https://github.com/JeromeTH/search-gym
format Preprint
id arxiv_https___arxiv_org_abs_2603_04402
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SearchGym: A Modular Infrastructure for Cross-Platform Benchmarking and Hybrid Search Orchestration
Hsu, Jerome Tze-Hou
Information Retrieval
Computation and Language
The rapid growth of Retrieval-Augmented Generation (RAG) has created a proliferation of toolkits, yet a fundamental gap remains between experimental prototypes and robust, production-ready systems. We present SearchGym, a modular infrastructure designed for cross-platform benchmarking and hybrid search orchestration. Unlike existing model-centric frameworks, SearchGym decouples data representation, embedding strategies, and retrieval logic into stateful abstractions: Dataset, VectorSet, and App. This separation enables a Compositional Config Algebra, allowing designers to synthesize entire systems from hierarchical configurations while ensuring perfect reproducibility. Moreover, we analyze the "Top-$k$ Cognizance" in hybrid retrieval pipelines, demonstrating that the optimal sequence of semantic ranking and structured filtering is highly dependent on filter strength. Evaluated on the LitSearch expert-annotated benchmark, SearchGym achieves a 70% Top-100 retrieval rate. SearchGym reveals a design tension between generalizability and optimizability, presenting the potential where engineering optimization may serve as a tool for uncovering the causal mechanisms inherent in information retrieval across heterogeneous domains. An open-source implementation of SearchGym is available at: https://github.com/JeromeTH/search-gym
title SearchGym: A Modular Infrastructure for Cross-Platform Benchmarking and Hybrid Search Orchestration
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2603.04402