# ResearchTown: Simulator of Human Research Community

arXiv: https://arxiv.org/abs/2412.17767 · HTML: https://mlsanity.com/paper/2412.17767/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 27 of 27)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Learning on Large-scale Text-attributed Graphs via Variational Inference](https://mlsanity.com/paper/2210.14709/) (2022)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph](https://mlsanity.com/paper/2105.02605/) (2021)
- [The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4](https://mlsanity.com/paper/2311.07361/) (2023)
- [Label-free Node Classification on Graphs with Large Language Models (LLMS)](https://mlsanity.com/paper/2310.04668/) (2023)
- [4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models](https://mlsanity.com/paper/2406.07472/) (2024)
- [Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas](https://mlsanity.com/paper/2410.14255/) (2024)
- [Learning Multi-Agent Communication from Graph Modeling Perspective](https://mlsanity.com/paper/2405.08550/) (2024)
- [Stochastic Optimal Control Matching](https://mlsanity.com/paper/2312.02027/) (2023)
- [On the Worst Prompt Performance of Large Language Models](https://mlsanity.com/paper/2406.10248/) (2024)
- [Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes](https://mlsanity.com/paper/2405.17580/) (2024)
- [Agent-based Graph Neural Networks](https://mlsanity.com/paper/2206.11010/) (2022)
- [Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning](https://mlsanity.com/paper/2205.12532/) (2022)
- [Longitudinal Citation Prediction using Temporal Graph Neural Networks](https://mlsanity.com/paper/2012.05742/) (2020)
- [Multistable Shape from Shading Emerges from Patch Diffusion](https://mlsanity.com/paper/2405.14530/) (2024)

## Built on by (most cited first, 30 of 37)

- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [AI Scientists Fail Without Strong Implementation Capability](https://mlsanity.com/paper/2506.01372/) (2025)
- [SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents](https://mlsanity.com/paper/2505.23559/) (2025)
- [How Far Are AI Scientists from Changing the World?](https://mlsanity.com/paper/2507.23276/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Can We Predict Before Executing Machine Learning Agents?](https://mlsanity.com/paper/2601.05930/) (2026)
- [Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance](https://mlsanity.com/paper/2601.14171/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems](https://mlsanity.com/paper/2503.01424/) (2025)
- [Exploring Design of Multi-Agent LLM Dialogues for Research Ideation](https://mlsanity.com/paper/2507.08350/) (2025)
- [PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation](https://mlsanity.com/paper/2508.21720/) (2025)
- [TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents](https://mlsanity.com/paper/2510.06579/) (2025)
- [Learning to Predict Future-Aligned Research Proposals with Language Models](https://mlsanity.com/paper/2603.27146/) (2026)
- [Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives](https://mlsanity.com/paper/2502.04358/) (2025)
- [Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network](https://mlsanity.com/paper/2511.02238/) (2025)
- [Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs](https://mlsanity.com/paper/2602.07276/) (2026)
- [The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research](https://mlsanity.com/paper/2602.18458/) (2026)
- [DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal](https://mlsanity.com/paper/2601.18081/) (2026)
- [AcademicEval: Live Long-Context LLM Benchmark](https://mlsanity.com/paper/2510.17725/) (2025)
- [PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling](https://mlsanity.com/paper/2511.16883/) (2025)
- [The Ramon Llull's Thinking Machine for Automated Ideation](https://mlsanity.com/paper/2508.19200/) (2025)
- [SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence](https://mlsanity.com/paper/2512.22334/) (2025)
- [Federation over Text: Insight Sharing for Multi-Agent Reasoning](https://mlsanity.com/paper/2604.16778/) (2026)
- [Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents](https://mlsanity.com/paper/2606.31229/) (2026)
- [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026)
- [Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework](https://mlsanity.com/paper/2604.06170/) (2026)
- [Can Large Language Models Forecast What Researchers Study Next?](https://mlsanity.com/paper/2609.00747/) (2026)
- [RouteProfile: Graph-Based Profiling for Cold-Start LLM Routing](https://mlsanity.com/paper/2605.00180/) (2026)
- [SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents](https://mlsanity.com/paper/2606.08234/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable potential in scientific domains, yet a fundamental question remains unanswered: Can we simulate human research communities with LLMs? Addressing this question can deepen our understanding of the processes behind idea brainstorming and inspire the automatic discovery of novel scientific insights. In this work, we propose ResearchTown, a multi-agent framework for research community simulation. Within this framework, the human research community is simplified as an agent-data graph, where researchers and papers are represented as agent-type and data-type nodes, respectively, and connected based on their collaboration relationships. We also introduce TextGNN, a text-based inference framework that models various research activities (e.g., paper reading, paper writing, and review writing) as special forms of a unified message-passing process on the agent-data graph. To evaluate the quality of the research community simulation, we present ResearchBench, a benchmark that uses a node-masking prediction task for scalable and objective assessment based on similarity. Our experiments reveal three key findings: (1) ResearchTown can provide a realistic simulation of collaborative research activities, including paper writing and review writing; (2) ResearchTown can maintain robust simulation with multiple researchers and diverse papers; (3) ResearchTown can generate interdisciplinary research ideas that potentially inspire pioneering research directions.