@inproceedings{an-yang-2026-moose,
title = "{MOOSE}-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery",
author = "An, Hongran and
Yang, Zonglin",
editor = "Durrett, Greg and
Jian, Ping",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-demo.85/",
pages = "861--869",
ISBN = "979-8-89176-392-0",
abstract = "Large language models (LLMs) show remarkable potential in scientific hypothesis discovery. However, existing approaches face two critical limitations: they treat divergent exploratory search and convergent fine-grained refinement as isolated tasks, and they operate autonomously with little to no human guidance. We present MOOSE-Copilot, the first unified framework to bridge this abstraction gap through a formalized human{--}AI interaction (HAII) protocol. Our system empowers scientists to steer the generative process via three explicit signals: initial blueprints, inter-stage routing, and intra-stage feedback. Using an oracle-simulated evaluation in which an LLM provides idealized expert signals, we show that injecting these structured signals significantly outperforms purely autonomous baselines, characterizing the gains achievable under high-quality guidance. Furthermore, we build a web-based interface that turns the framework into a no-code workflow: researchers pose a question, watch the hypothesis search unfold as an interactive tree, and steer it by selecting hypotheses, routing between stages, and injecting feedback{---}no command-line agents required. This makes end-to-end hypothesis discovery directly accessible to interdisciplinary researchers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-yang-2026-moose">
<titleInfo>
<title>MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongran</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zonglin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-392-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) show remarkable potential in scientific hypothesis discovery. However, existing approaches face two critical limitations: they treat divergent exploratory search and convergent fine-grained refinement as isolated tasks, and they operate autonomously with little to no human guidance. We present MOOSE-Copilot, the first unified framework to bridge this abstraction gap through a formalized human–AI interaction (HAII) protocol. Our system empowers scientists to steer the generative process via three explicit signals: initial blueprints, inter-stage routing, and intra-stage feedback. Using an oracle-simulated evaluation in which an LLM provides idealized expert signals, we show that injecting these structured signals significantly outperforms purely autonomous baselines, characterizing the gains achievable under high-quality guidance. Furthermore, we build a web-based interface that turns the framework into a no-code workflow: researchers pose a question, watch the hypothesis search unfold as an interactive tree, and steer it by selecting hypotheses, routing between stages, and injecting feedback—no command-line agents required. This makes end-to-end hypothesis discovery directly accessible to interdisciplinary researchers.</abstract>
<identifier type="citekey">an-yang-2026-moose</identifier>
<location>
<url>https://aclanthology.org/2026.acl-demo.85/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>861</start>
<end>869</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
%A An, Hongran
%A Yang, Zonglin
%Y Durrett, Greg
%Y Jian, Ping
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-392-0
%F an-yang-2026-moose
%X Large language models (LLMs) show remarkable potential in scientific hypothesis discovery. However, existing approaches face two critical limitations: they treat divergent exploratory search and convergent fine-grained refinement as isolated tasks, and they operate autonomously with little to no human guidance. We present MOOSE-Copilot, the first unified framework to bridge this abstraction gap through a formalized human–AI interaction (HAII) protocol. Our system empowers scientists to steer the generative process via three explicit signals: initial blueprints, inter-stage routing, and intra-stage feedback. Using an oracle-simulated evaluation in which an LLM provides idealized expert signals, we show that injecting these structured signals significantly outperforms purely autonomous baselines, characterizing the gains achievable under high-quality guidance. Furthermore, we build a web-based interface that turns the framework into a no-code workflow: researchers pose a question, watch the hypothesis search unfold as an interactive tree, and steer it by selecting hypotheses, routing between stages, and injecting feedback—no command-line agents required. This makes end-to-end hypothesis discovery directly accessible to interdisciplinary researchers.
%U https://aclanthology.org/2026.acl-demo.85/
%P 861-869
Markdown (Informal)
[MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery](https://aclanthology.org/2026.acl-demo.85/) (An & Yang, ACL 2026)
ACL