ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models
Authors: Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, Sung Ju Hwang
Abstract
Scientific Research, vital for improving human life, is hindered by its inherent complexity, slow pace, and the need for specialized experts. To enhance its productivity, we propose a ResearchAgent, a large language model-powered research idea writing agent, which automatically generates problems, methods, and experiment designs while iteratively refining them based on scientific literature. Specifically, starting with a core paper as the primary focus to generate ideas, our ResearchAgent is augmented not only with relevant publications through connecting information over an academic graph but also entities retrieved from an entity-centric knowledge store based on their underlying concepts, mined and shared across numerous papers. In addition, mirroring the human approach to iteratively improving ideas with peer discussions, we leverage multiple ReviewingAgents that provide reviews and feedback iteratively. Further, they are instantiated with human preference-aligned large language models whose criteria for evaluation are derived from actual human judgments. We experimentally validate our ResearchAgent on scientific publications across multiple disciplines, showcasing its effectiveness in generating novel, clear, and valid research ideas based on human and model-based evaluation results.
The papers around it, by date and closeness
Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper
Papers around this one
Ranked by how close their title and abstract are to this paper’s. Select some to read them together.
Closest papers
-
BioLabAgents: A Multi-Agent Framework for Scientific Idea Generation and Evaluation on Biomedical Research TrajectoriesYan Li, Wuyang Lan, Changwei Ji et al. · 2025 · IEEE International Conference on Bioinformatics and Biomedicine · cited 1 time · Not summarized yet
Abstract
Advancing biomedical discovery demands creative, well grounded research ideas, yet early stage ideation remains slow, resource-intensive, and uncertain. Recent large language model (LLM) systems show promise for idea generation, but their outputs are rarely evaluated for their potential to meaningfully advance research trajectories. Here we present BioLabAgents, a multi-agent framework that emulates collaborative research for scientific idea generation, where specialized LLM agents iteratively propose, critique, and refine research problems, methods, and experimental designs from a single seed publication. To assess the plausibility and forward-driving value of generated scientific ideas, we…
-
Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM AgentsLong Li, Wei-Wen Xu, Jiayan Guo et al. · 2024 · Conference on Empirical Methods in Natural Language Processing · cited 133 times · Not summarized yet
Abstract
Effective research ideation is a critical step for scientific research. However, the exponential increase in scientific literature makes it challenging for researchers to stay current with recent advances and identify meaningful research directions. Recent developments in large language models~(LLMs) suggest a promising avenue for automating the generation of novel research ideas. However, existing methods for idea generation either trivially prompt LLMs or directly expose LLMs to extensive literature without indicating useful information. Inspired by the research process of human researchers, we propose a Chain-of-Ideas~(CoI) agent, an LLM-based agent that organizes relevant literature in a…
-
GraphingAgent: An Agentic RAG Framework for Automated Knowledge Discovery in Scientific LiteratureNivedha Raut, Rupali V. Pashte · 2025 · 2025 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA) · Not summarized yet
Abstract
The exponential growth of research articles has made it increasingly difficult for researchers to manually search and mine relevant problems. Traditional search mechanisms often fail to capture contextual nuances, leading to information overload. This paper proposes an automated framework that leverages large language models (LLMs), prompt engineering, and vector databases to efficiently mine and graph research problems. By integrating a retrieval-augmented generation (RAG) ecosystem with catered prompts and a retrieval chain, the system provides structured access to research problem statements in an open-access environment. Experimental implementation demonstrates the potential of this syst…
-
Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept NetworkKe-Yu Zhao, Weiquan Lin, Qirui Zheng et al. · 2025 · arXiv.org · preprint, not peer reviewed · cited 8 times · Not summarized yet
Abstract
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"keywo…
-
Analysis of Accelerating Ideation Process with Large Language ModelYuhan Wei · 2024 · Applied and Computational Engineering · cited 1 time · Not summarized yet
Abstract
Abstract. Large Language Models (LLMs) have rapidly advanced, demonstrating near-human intelligence in language comprehension, problem-solving, and autonomous decision-making, which can be leveraged in scientific discovery. Previous research of LLM for science often focuses on experiment execution part and the first stage of research, i.e., idea generation with large language models is lack of research. This paper fills this gap by surveying the use of LLM-based agent systems in research idea generation. This research first proposes three stages in research idea generation pipeline, pre-ideation (knowledge preparation), ideation (generation and iteration), post-ideation (evaluation), and pro…
-
AI Research Agents Narrow Scientific ExplorationYixuan Tang, Yi Yang · 2026 · arXiv.org · preprint, not peer reviewed · cited 4 times · Not summarized yet
Abstract
AI research agents now support large-scale AI-assisted scientific discovery. We examine whether AI-generated ideas broaden scientific exploration or primarily reinforce existing work. Using five agent frameworks and five large language models, we generate 219,655 ideas for different scientific fields. Across experiments, four consistent patterns emerge. First, AI-generated ideas are more concentrated than human-authored papers within the same research area. Second, they remain much closer to starting literature than later human follow-on work does. Third, AI-generated ideas align less with future human research. Last, AI-generated ideas are located in lower-impact regions of the historical s…
-
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific NarrativesT. Xu, Z. Qian, Gao Liu et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 8 times · Not summarized yet
Abstract
Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowl…
-
The AI Scientist: Towards Fully Automated Open-Ended Scientific DiscoveryChris Lu, Cong Lu, Robert Tjarko Lange et al. · 2024 · Artificial Intelligence · preprint, not peer reviewed · cited 1,350 times · AI summary available
Abstract
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aids to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its …
Prior work it builds on
-
Benchmarking Large Language Models As AI Research AgentsQian Huang, Jian Vora, Percy Liang et al. · 2023 · arXiv.org · preprint, not peer reviewed · cited 67 times · Not summarized yet
-
Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, A. Torralba et al. · 2023 · International Conference on Machine Learning · cited 2,570 times · Not summarized yet
Abstract
Large language models (LLMs) have demonstrated remarkable capabilities in language generation, understanding, and few-shot learning in recent years. An extensive body of work has explored how their performance may be further improved through the tools of prompting, ranging from verification, self-consistency, or intermediate scratchpads. In this paper, we present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a nu…
-
How AI Processing Delays Foster Creativity: Exploring Research Question Co-Creation with an LLM-based AgentYi-Ren Liu, Si Chen, Haocong Cheng et al. · 2023 · International Conference on Human Factors in Computing Systems · cited 116 times · Not summarized yet
Abstract
Developing novel research questions (RQs) often requires extensive literature reviews, especially in interdisciplinary fields. To support RQ development through human-AI co-creation, we leveraged Large Language Models (LLMs) to build an LLM-based agent system named CoQuest. We conducted an experiment with 20 HCI researchers to examine the impact of two interaction designs: breadth-first and depth-first RQ generation. The findings revealed that participants perceived the breadth-first approach as more creative and trustworthy upon task completion. Conversely, during the task, participants considered the depth-first generated RQs as more creative. Additionally, we discovered that AI processing…
-
Large Language Models for Automated Open-domain Scientific Hypotheses DiscoveryZonglin Yang, Xinya Du, Jun-Xian Li et al. · 2023 · Annual Meeting of the Association for Computational Linguistics · cited 144 times · Not summarized yet
Abstract
Hypothetical induction is recognized as the main reasoning type when scientists make observations about the world and try to propose hypotheses to explain those observations. Past research on hypothetical induction is under a constrained setting: (1) the observation annotations in the dataset are carefully manually handpicked sentences (resulting in a close-domain setting); and (2) the ground truth hypotheses are mostly commonsense knowledge, making the task less challenging. In this work, we tackle these problems by proposing the first dataset for social science academic hypotheses discovery, with the final goal to create systems that automatically generate valid, novel, and helpful scienti…
-
AGATHA: Automatic Graph Mining And Transformer based Hypothesis Generation ApproachJustin Sybrandt, Ilya Tyagin, M. Shtutman et al. · 2020 · International Conference on Information and Knowledge Management · cited 55 times · Not summarized yet
Abstract
Medical research is risky and expensive. Drug discovery requires researchers to efficiently winnow thousands of potential targets to a small candidate set. However, scientists spend significant time and money long before seeing the intermediate results that ultimately determine this smaller set. Hypothesis generation systems address this challenge by mining the wealth of publicly available scientific information to predict plausible research directions. We present AGATHA, a deep-learning hypothesis generation system that learns a data-driven ranking criteria to recommend new biomedical connections. We massively validate our system with a temporal holdout wherein we predict connections first …
Papers that cite it
-
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and EvaluationSteffen Eger, Yong Cao, Jennifer D'Souza et al. · 2025 · Computation and Language · cited 63 times · AI summary available
Transforming Science with Large Language Models surveys AI tools across scientific discovery, including research-idea generation and automated peer review.
Abstract
With the advent of large multimodal language models, science is now at a threshold of an AI-based technological transformation. Recently, a plethora of new AI models and tools has been proposed, promising to empower researchers and academics worldwide to conduct their research more effectively and efficiently. This includes all aspects of the research cycle, especially (1) searching for relevant literature; (2) generating research ideas and conducting experimentation; generating (3) text-based and (4) multimodal content (e.g., scientific figures and diagrams); and (5) AI-based automatic peer review. In this survey, we provide an in-depth overview over these exciting recent developments, whic…
-
PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop RefinementWei Ye, Hang-Chen Liu, Dong-Yuan Li et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet
Abstract
Large language models have become capable reasoners and tool users that write and run code and search the literature, which makes automating the research process itself a realistic goal. We present PAPERCLAW, a harnessed multi-agent system that carries a project autonomously, from a field of study to a finished paper. PAPERCLAW curates a domain from a field's live literature, datasets, and code; brainstorms it into an idea with a pre-registered main-result contract; and drives a stoppable hypothesis map through an iterative propose, test, reflect loop that grows only from measured verdicts and halts once the evidence supports the idea, at which point it writes a venue-compliant paper. A full…
-
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured ContextsXu Li, Hanzhe Tu, Xun Han · 2026 · arXiv.org · preprint, not peer reviewed · cited 4 times · Not summarized yet
Abstract
Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery. Recent Large Language Model (LLM)-based methods often ground idea generation with retrieved literature, but the retrieved evidence is usually provided as flat text, such as titles, abstracts, or summaries. Such flat contexts may contain redundant or weakly relevant information, while making cross-paper relations among problems, methods, mechanisms, and findings difficult to identify and trace. To address this challenge, we propose Graph2Idea, a knowledge graph-guided framework for retrieval-augmented scientific idea generation.Graph2Idea first retrieves papers according t…
-
EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea GenerationXu Li, Hanzhe Tu, Xin-Yi Li et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 2 times · Not summarized yet
Abstract
Generating novel research ideas is fundamental to scientific progress. While Large Language Models (LLMs) show promise in assisting this process, existing approaches often exhibit semantic convergence, resulting in limited diversity and novelty. To address this, we introduce EvoGens, an evolution-inspired framework that recasts scientific idea generation as an evolutionary search over a population of ideas. EvoGens iteratively applies rank-based mutation with differentiated retrieval planning to incorporate external knowledge, and semantic-aware crossover to fuse complementary concepts for conceptual reorganization. A lightweight evaluation signal guides the selection process, encouraging su…
-
Distill, Debate, Discover: Grounding Multi-Agent Research Ideation in Graph-Distilled InsightsQian-Ran Ma, Mu-Xin-Wang-Xu-Zhu-Hai-Biao Liu, Grace Kim et al. · 2026 · Not summarized yet
Abstract
Large language models (LLMs) are increasingly used to support research idea generation and scientific discovery. Multi-agent debate offers a collaborative approach to this task by bringing together diverse perspectives to develop research ideas. However, a key challenge is how to equip agents with distinct and meaningful expertise to guide their contributions. Inspired by how researchers draw on accumulated research experience during collaboration, we introduce InsightAgents, a framework that constructs literature-grounded agent expertise by distilling insights from graphs of related papers. Guided by insights that trace evolving research approaches, reveal underlying assumptions, and identi…
Go further
How are these papers found?
We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.
Updated on 1 November 2026.