IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Garikaparthi, Aniketh, Patwardhan, Manasi, Vig, Lovekesh, Cohan, Arman
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909621810102272
author Garikaparthi, Aniketh
Patwardhan, Manasi
Vig, Lovekesh
Cohan, Arman
author_facet Garikaparthi, Aniketh
Patwardhan, Manasi
Vig, Lovekesh
Cohan, Arman
contents The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent work on automated hypothesis generation focuses on multi-agent frameworks and extending test-time compute, none of the approaches effectively incorporate transparency and steerability through a synergistic Human-in-the-loop (HITL) approach. To address this gap, we introduce IRIS: Interactive Research Ideation System, an open-source platform designed for researchers to leverage LLM-assisted scientific ideation. IRIS incorporates innovative features to enhance ideation, including adaptive test-time compute expansion via Monte Carlo Tree Search (MCTS), fine-grained feedback mechanism, and query-based literature synthesis. Designed to empower researchers with greater control and insight throughout the ideation process. We additionally conduct a user study with researchers across diverse disciplines, validating the effectiveness of our system in enhancing ideation. We open-source our code at https://github.com/Anikethh/IRIS-Interactive-Research-Ideation-System
format Preprint
id arxiv_https___arxiv_org_abs_2504_16728
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery
Garikaparthi, Aniketh
Patwardhan, Manasi
Vig, Lovekesh
Cohan, Arman
Artificial Intelligence
Computation and Language
Human-Computer Interaction
The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent work on automated hypothesis generation focuses on multi-agent frameworks and extending test-time compute, none of the approaches effectively incorporate transparency and steerability through a synergistic Human-in-the-loop (HITL) approach. To address this gap, we introduce IRIS: Interactive Research Ideation System, an open-source platform designed for researchers to leverage LLM-assisted scientific ideation. IRIS incorporates innovative features to enhance ideation, including adaptive test-time compute expansion via Monte Carlo Tree Search (MCTS), fine-grained feedback mechanism, and query-based literature synthesis. Designed to empower researchers with greater control and insight throughout the ideation process. We additionally conduct a user study with researchers across diverse disciplines, validating the effectiveness of our system in enhancing ideation. We open-source our code at https://github.com/Anikethh/IRIS-Interactive-Research-Ideation-System
title IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery
topic Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2504.16728