OpenIIR: An Open Simulation Platform for Information Retrieval Research
For IR researchers, OpenIIR offers a standardized, reproducible simulation environment to study multi-agent information retrieval scenarios, though it is an incremental tool rather than a breakthrough.
OpenIIR is an open simulation platform that enables reproducible, parameterised IR research experiments with hundreds of LLM-driven personas across four multi-agent study types. It provides structured outputs for downstream evaluation and a plug-in architecture for new studies.
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.