Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution
Not on the map. Why?
Abstract (arXiv)
Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature. Existing methods either treat papers as unstructured context or model scholarly evolution as isolated citation chains, overlooking interactions among research trajectories. We propose Tree-of-Ideas (ToI), a two-stage framework. EvoTrace reconstructs branching scholarly trajectories from citations, tracking evolving methods, resolved problems, and gaps. EvoAgent then reasons across trajectories to identify convergent problems and complementary solutions, generating grounded research ideas. Across six AI research topics, ToI achieves the highest score among automatic methods (6.27 vs. 5.36 for the strongest baseline on a 10-point scale), with strong Novelty (6.36) and Groundedness (7.00). Also, its score approaches that of human-paper references (6.29), demonstrating the value of cross-path evolutionary reasoning.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 41 references that are in the map. First posted on arXiv 11 Aug 2026.
Builds on
25 of 41 references.
References · 25
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2019Language Models as Knowledge Bases?cited by 1,936
- 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
- 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
- 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 575
- 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 430
- 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
- 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
- 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
13 more
- 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
- 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
- 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 179
- 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 148
- 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
- 2018Construction of the Literature Graph in Semantic Scholarcited by 118
- 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 97
- 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
- 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Researchcited by 64
- 2025The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideascited by 62
- 2024Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideascited by 57
- 2025AI Idea Bench 2025: AI Research Idea Generation Benchmarkcited by 40
- 2025MIR: Methodology Inspiration Retrieval for Scientific Research Problemscited by 11
Built on by
Citing papers per year: 2026: 1.
1 paper.