Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline. A key capability for this process is the ability to generate novel research ideas, and prior studies have found settings in which LLM-generated research ideas were judged as more novel than human-expert ideas. However, a good idea should not simply appear to be novel, it should also result in better research after being executed. To test whether AI-generated ideas lead to better research outcomes, we conduct an execution study by recruiting 43 expert researchers to execute randomly-assigned ideas, either written by experts or generated by an LLM. Each expert spent over 100 hours implementing the idea and wrote a 4-page short paper to document the experiments. All the executed projects are then reviewed blindly by expert NLP researchers. Comparing the review scores of the same ideas before and after execution, the scores of the LLM-generated ideas decrease significantly more than expert-written ideas on all evaluation metrics (novelty, excitement, effectiveness, and overall; p < 0.05), closing the gap between LLM and human ideas observed at the ideation stage. When comparing the aggr
Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows.
LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert preference. We instead ask: how far are current LLM-generated ideas from human researchers? To characterize this gap, we build a large-scale evaluation framework for ideation from high-quality human research papers. For each paper, we reverse-engineer a small set of closely related prior works that likely inspired its core idea. LLMs are then prompted to generate a new idea from the set of paper titles and summaries. We introduce a two-axis research-taste taxonomy to profile each idea by its opportunity pattern and research paradigm, and use it to quantify the divergence between human and LLM ideas. Across idea sets generated by different LLMs, we observe a consistent distributional gap: LLM ideas are disproportionately concentrated around bridge-like opportunities and synthesis methods, whereas the human paper reference distribution spreads more broadly across ways of framing gaps and constructing contributions. This result suggests that strong LLMs can produce a range of reasonable ideas, but that range remains narrower than, and syste
This paper describes the method for ex-post peer review evaluation per research discipline used at the Vrije Universiteit Brussel (VUB) and summarizes the outcomes obtained from it. The method produces pertinent advice and triggers responses - at the level of the individual researcher, the research team and the university's research management - for the benefit of research quality, competitivity and visibility. Imposed reflection and contacts during and after the evaluation procedure modify the individual researcher's attitude, improve the research teams' strategies and allow for the extraction of general recommendations that are used as discipline-dependent guidelines in the university's research management. The deep insights gained in the different research disciplines and the substantial data sets on their research, support the university management in its policy decisions and in building policy instruments. Moreover, the results are used as a basis for comparison with other assessments, leading to a better understanding of the possibilities and limitations of different evaluation processes. The peer review method can be applied systematically in a pluri-annual cycle of research
Despite the importance of social science knowledge for various stakeholders, measuring its diffusion into different domains remains a challenge. This study uses a novel text-based approach to measure the idea-level diffusion of social science knowledge from the research domain to the journalism and policy-making domains. By doing so, we expand the detection of knowledge diffusion beyond the measurements of direct references. Our study focuses on media effects theories as key research ideas in the field of communication science. Using 72,703 documents (2000-2019) from three domains (i.e., research, journalism, and policy-making) that mention these ideas, we count the mentions of these ideas in each domain, estimate their domain-specific contexts, and track and compare differences across domains and over time. Overall, we find that diffusion patterns and dynamics vary considerably between ideas, with some ideas diffusing between other domains, while others do not. Based on the embedding regression approach, we compare contextualized meanings across domains and find that the distances between research and policy are typically larger than between research and journalism. We also find t
Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must ground a problem in current literature, identify meaningful bottlenecks, differentiate from existing solutions, and evaluate risks before committing to implementation. We present ResearchStudio-Idea as a reusable skill suite for this first mile of research ideation. The suite includes Paper-Search, a standalone multi-source literature search skill; Scoop-Check, a standalone prior-art collision checker for novelty claims; and IdeaSpark, the end-to-end skill that composes evidence grounding, pattern-guided generation, collision retrieval, audit, and idea-card rendering into one workflow. IdeaSpark is constructed from a corpus of 1,947 machine learning conference papers collected from ICLR, ICML, and NeurIPS between 2021 and 2025, including Oral papers, a separately tracked high-citation subset, and rejected submissions. Analysis of these outcomes reveals 31 recurring ideation sub-patterns, consolidated into 15 reusable ideation patterns. Each pattern is operationalized as a structured card containing research co
Judging the novelty of research ideas is crucial for advancing science, enabling the identification of unexplored directions, and ensuring contributions meaningfully extend existing knowledge rather than reiterate minor variations. However, given the exponential growth of scientific literature, manually judging the novelty of research ideas through literature reviews is labor-intensive, subjective, and infeasible at scale. Therefore, recent efforts have proposed automated approaches for research idea novelty judgment. Yet, evaluation of these approaches remains largely inconsistent and is typically based on non-standardized human evaluations, hindering large-scale, comparable evaluations. To address this, we introduce RINoBench, the first comprehensive benchmark for large-scale evaluation of research idea novelty judgments. It comprises 1,381 research ideas derived from and judged by human experts as well as nine automated evaluation metrics designed to assess both rubric-based novelty scores and textual justifications of novelty judgments. Using this benchmark, we evaluate several state-of-the-art large language models (LLMs) on their ability to judge the novelty of research ideas
Recent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that autonomously generate and validate new ideas. Despite this, no evaluations have shown that LLM systems can take the very first step of producing novel, expert-level ideas, let alone perform the entire research process. We address this by establishing an experimental design that evaluates research idea generation while controlling for confounders and performs the first head-to-head comparison between expert NLP researchers and an LLM ideation agent. By recruiting over 100 NLP researchers to write novel ideas and blind reviews of both LLM and human ideas, we obtain the first statistically significant conclusion on current LLM capabilities for research ideation: we find LLM-generated ideas are judged as more novel (p < 0.05) than human expert ideas while being judged slightly weaker on feasibility. Studying our agent baselines closely, we identify open problems in building and evaluating research agents, including failures of LLM self-evaluation and their lack of diversity in generation. Fin
Academic, peer-reviewed short papers are a common way to present a late-breaking work to the academic community that outlines preliminary findings, research ideas, and novel conversations. By comparison, blogging or writing posts on social media are an unstructured and open way to discuss ideas and start new conversations. Both have limitations in the proliferation of research ideas. The short paper format relies on the conference and journal submission process while blogging does not operate within a structured format or set of expectations at all. However, at times the demand exists for late-breaking ideas and conversations to arise in a raw form or with urgency but should still be archived and recorded in a way that promotes citational honesty and integrity. To address this, I present: The Micro-Paper, as a micro-paper itself. The Micro-Paper is a small, cheap, accessible, digital document that is self-published and archived, akin to a pre-print of a short paper. This meta micro-paper discusses the context, goals, and considerations of micro-paper authoring.
The rapid growth of scientific literature makes it challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new approaches, potentially inspiring ideas not conceived by humans alone. But how compelling are these AI-generated ideas, and how can we improve their quality? Here, we introduce SciMuse, which uses 58 million research papers and a large-language model to generate research ideas. We conduct a large-scale evaluation in which over 100 research group leaders -- from natural sciences to humanities -- ranked more than 4,400 personalized ideas based on their interest. This data allows us to predict research interest using (1) supervised neural networks trained on human evaluations, and (2) unsupervised zero-shot ranking with large-language models. Our results demonstrate how future systems can help generating compelling research ideas and foster unforeseen interdisciplinary collaborations.
Modern research heavily relies on software. A significant challenge researchers face is understanding the complex software used in specific research fields. We target two scenarios in this context, namely long onboarding times for newcomers and conference reviewers evaluating replication packages. We hypothesize that both scenarios can be significantly improved when there is a clear link between the paper's ideas and the code that implements them. As a time- and staff-saving approach, we propose an LLM-based automation tool that takes in a paper and the software implementing the paper, and generates a trace mapping between research ideas and their locations in code. Initial experiments have shown that the tool can generate quite useful mappings.
Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas they produce are often repetitive and lack depth. To address this issue, this study proposes a multi-agent iterative planning search strategy inspired by com-binatorial innovation theory. The framework combines iterative knowledge search with an LLM-based multi-agent system to generate, evaluate, and re-fine research ideas through repeated interaction, with the goal of improving idea diversity and novelty. Experiments in the natural language processing domain show that the proposed method outperforms state-of-the-art base-lines in both diversity and novelty. Further comparison with ideas derived from top-tier machine learning conference papers indicates that the quality of the generated ideas falls between that of accepted and rejected papers. These results suggest that the proposed framework is a promising approach for s
Demographic data collection is essential in education research, as demographic data allows researchers to better describe the participant population they study and to contextualize findings. However, current research practices for neurodiversity demographics often rely on prescriptive methods (e.g., requiring participants to report official diagnoses) rather than allowing participants to self-identify. This approach can: a) not allow participants to express their intersecting identities in ways that are authentic; and b) limit trustworthiness and reliability of the data and interpretation. In addition, inconsistent dissemination and representation of demographic data across studies hinder the accessibility and usability of this work. Through a literature review of neurodivergent student experiences with learning and performing STEM, we identified widespread discrepancies in how demographic information is collected and reported. This paper explores how neurodivergent identities can be more accurately and inclusively represented in education research. We present findings of a thematic analysis on the ways neurodivergent demographic data collection is done in the literature using data
Machine learning research increasingly bifurcates into two disconnected modes: benchmark-driven engineering that prioritizes metrics over understanding, and idealized theory that often fails to transfer to modern systems. In this position paper, we argue that the field focuses too heavily on these endpoints, neglecting the central scientific object: the idea. We propose an Ideas First framework in which ideas are valued for the behavioral signatures they predict in modern models, and these signatures are tested through tailored experiments designed to detect the relevant patterns rather than to win leaderboards. This shift not only bridges the gap between theory and practice but also promotes equity by removing the "complexity premium," enabling rigorous scientific contributions from researchers with modest computational, financial, and human resources. Ultimately, we advocate for a research culture centered on ideas, treating benchmarks and theorems as instruments for testing mechanistic hypotheses rather than as ends in themselves.
In the Summer of 2020, as COVID-19 limited in-person research opportunities and created additional barriers for many students, institutions either canceled or remotely hosted their Research Experience for Undergraduates (REU) programs. The present longitudinal qualitative phenomenographic study was designed to explore some of the possible limitations, challenges and outcomes of this remote experience. Overall, 94 interviews were conducted with paired participants; mentees (N=10) and mentors (N=8) from six different REU programs. By drawing on Cultural-Historical Activity Theory (CHAT) as a framework, our study uncovers some of the challenges for mentees around the accomplishment of their research objectives and academic goals. These challenges included motivation, limited access to technologies at home, limited communication among REU students, barriers in mentor-mentee relationships, and differing expectations about doing research. Despite the challenges, all mentees reported that this experience was highly beneficial. Comparisons between outcomes of these remote REUs and published outcomes of in-person undergraduate research programs reveal many similar benefits such as integrati
Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scale scientific literature. However, previous work in research ideation has primarily relied on simplistic methods, such as keyword co-occurrence or semantic similarity. These approaches focus on identifying statistical associations in the literature but overlook the complex, contextual relationships between scientific concepts, which are essential to effectively leverage knowledge embedded in human literature. For instance, papers that simultaneously mention "keyword A" and "keyword B" often present research ideas that integrate both concepts. Additionally, some LLM-driven methods propose and refine research ideas using the model's internal knowledge, but they fail to effectively utilize the scientific concept network, limiting the grounding of ideas in established research. To address these challenges, we propose the Deep Ideation framework to address these challenges, integrating a scientific network that captures keyword co-occurrence and contextual relationships,
This paper presents a scientometric analysis of research output from the University of Lagos, focusing on the two decades spanning 2004 to 2023. Using bibliometric data retrieved from the Web of Science, we examine trends in publication volume, collaboration patterns, citation impact, and the most prolific authors, departments, and research domains at the university. The study reveals a consistent increase in research productivity, with the highest publication output recorded in 2023. Health Sciences, Engineering, and Social Sciences are identified as dominant fields, reflecting the university's interdisciplinary research strengths. Collaborative efforts, both locally and internationally, show a positive correlation with higher citation impact, with the United States and the United Kingdom being the leading international collaborators. Notably, open-access publications account for a significant portion of the university's research output, enhancing visibility and citation rates. The findings offer valuable insights into the university's research performance over the past two decades, providing a foundation for strategic planning and policy formulation to foster research excellence
Evaluating AI-generated research ideas typically relies on LLM judges or human panels -- both subjective and disconnected from actual research impact. We introduce HindSight, a time-split evaluation framework that measures idea quality by matching generated ideas against real future publications and scoring them by citation impact and venue acceptance. Using a temporal cutoff~$T$, we restrict an idea generation system to pre-$T$ literature, then evaluate its outputs against papers published in the subsequent 30 months. Experiments across 10 AI/ML research topics reveal a striking disconnect: LLM-as-Judge finds no significant difference between retrieval-augmented and vanilla idea generation ($p{=}0.584$), while HindSight shows the retrieval-augmented system produces 2.5$\times$ higher-scoring ideas ($p{<}0.001$). Moreover, HindSight scores are \emph{negatively} correlated with LLM-judged novelty ($ρ{=}{-}0.29$, $p{<}0.01$), suggesting that LLMs systematically overvalue novel-sounding ideas that never materialize in real research.
Predicting the outcomes of research ideas at their conceptual stage (i.e. before significant resources are committed) holds great potential for optimizing scientific resource allocation and research planning. While existing methods rely heavily on finished manuscripts or peer reviews, we propose a novel capability-aware framework that predicts paper acceptance and ratings using only author information and research ideas, without requiring full text or experimental results. Our approach integrates author information, (inferred) capability presentation, and research ideas through a three-way transformer architecture with flexible fusion mechanisms. We also introduce a two-stage architecture for learning the capability representation given the author information and idea. Experiments show that our method significantly outperform the single-way models by finetuning bert-base and bert-large, and the capability predicting significantly increase the predictive accuracy of the final model. The proposed method can be applied in both early-stage research outcome prediction and scientific resource allocation.
This report summarizes the research outcomes achieved by the research group at Hokkaido University under the funding program "Innovative Information and Communications Technology Research and Development (Commissioned Research)" of the National Institute of Information and Communications Technology (NICT). Although this report is primarily written for specialists in the fields of optics and computational science, the content has been concisely organized to ensure accessibility and interest for a broader readership.