ResearchTown: Simulador da Comunidade de Pesquisa Humana
ResearchTown: Simulator of Human Research Community
December 23, 2024
Autores: Haofei Yu, Zhaochen Hong, Zirui Cheng, Kunlun Zhu, Keyang Xuan, Jinwei Yao, Tao Feng, Jiaxuan You
cs.AI
Resumo
Os Modelos de Linguagem de Grande Escala (LLMs) têm demonstrado um potencial notável em domínios científicos, no entanto, uma questão fundamental permanece sem resposta: Podemos simular comunidades de pesquisa humanas com LLMs? Abordar essa questão pode aprofundar nossa compreensão dos processos por trás da geração de ideias e inspirar a descoberta automática de insights científicos inovadores. Neste trabalho, propomos ResearchTown, um framework multiagente para simulação de comunidades de pesquisa. Dentro desse framework, a comunidade de pesquisa humana é simplificada e modelada como um grafo agente-dados, onde pesquisadores e artigos são representados como nós do tipo agente e tipo de dados, respectivamente, e conectados com base em suas relações de colaboração. Também introduzimos TextGNN, um framework de inferência baseado em texto que modela várias atividades de pesquisa (por exemplo, leitura de artigos, escrita de artigos e escrita de revisões) como formas especiais de um processo unificado de passagem de mensagens no grafo agente-dados. Para avaliar a qualidade da simulação de pesquisa, apresentamos ResearchBench, um benchmark que utiliza uma tarefa de previsão de mascaramento de nós para avaliação escalável e objetiva com base em similaridade. Nossos experimentos revelam três descobertas-chave: (1) ResearchTown pode fornecer uma simulação realista de atividades de pesquisa colaborativa, incluindo a escrita de artigos e revisões; (2) ResearchTown pode manter uma simulação robusta com múltiplos pesquisadores e artigos diversos; (3) ResearchTown pode gerar ideias de pesquisa interdisciplinares que potencialmente inspiram novas direções de pesquisa.
English
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 and modeled 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 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 novel research directions.Summary
AI-Generated Summary
DeepSeek-R1: Incentivizando a Capacidade de Raciocínio em LLMs via
Aprendizado por ReforçoDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-R1: Incentivizando a Capacidade de Raciocínio em LLMs via
Aprendizado por Reforço
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang•Jan 22, 2025•3905
Relatório Técnico do Qwen2.5Qwen2.5 Technical Report
Relatório Técnico do Qwen2.5
Qwen2.5 Technical Report
Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zihan Qiu•Dec 19, 2024•36511
MiniMax-01: Dimensionamento de Modelos de Fundação com Atenção RelâmpagoMiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax-01: Dimensionamento de Modelos de Fundação com Atenção Relâmpago
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu•Jan 14, 2025•2886