OpenIIR: An Open Simulation Platform for Information Retrieval Research

TL;DR

OpenIIR is a flexible simulation platform enabling reproducible IR research experiments with multiple agent-driven scenarios and detailed structured outputs for analysis.

Contribution

It introduces a shared core, pluggable scenario interfaces, four reference types, and six modular extensions for open IR research.

Findings

Supports side-by-side comparison of different IR settings

Produces structured outputs like argument graphs and logs

Includes four reference scenario types with reference runs

Abstract

OpenIIR runs hundreds of LLM-driven personas as parameterised, reproducible IR research experiments. Researchers configure agents across four kinds of multi-agent study (deliberative panels, social platforms, curated recommender feeds, and evolutionary co-evolution between content producers and credibility detectors) under many priors, rounds, and constraints. Persona budgets, retrieval policies, ranker choices, intervention timings, and mutation rates are declared up front, and the same study can be re-run under different settings to compare outcomes side by side. Every run produces structured outputs (argument graphs, exposure logs, fitness traces, transcripts) that a downstream evaluator can consume directly, and a new study is a 200--400 line plug-in over a shared core (agent runtime, world-model store, retrieval primitives, claim extractor, persona ontology). The contributions are: (i) the shared core; (ii) a type interface for pluggable scenarios; (iii) four released types with reference runs (Panel, Social-Media, Curated-Feed, Multi-Generational); and (iv) six modular extensions sketched against open IR research questions.