{"work":{"id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","openalex_id":"https://openalex.org/W4417493576","doi":"10.1186/s12912-025-04245-9","arxiv_id":"2309.07864","raw_key":null,"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","authors":null,"authors_text":"Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong","year":2023,"venue":"cs.AI","abstract":"For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that can adapt to diverse scenarios. Due to the versatile capabilities they demonstrate, large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI), offering hope for building general AI agents. Many researchers have leveraged LLMs as the foundation to build AI agents and have achieved significant progress. In this paper, we perform a comprehensive survey on LLM-based agents. We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. Building upon this, we present a general framework for LLM-based agents, comprising three main components: brain, perception, and action, and the framework can be tailored for different applications. Subsequently, we explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation. Following this, we delve into agent societies, exploring the behavior and personality of LLM-based agents, the social phenomena that emerge from an agent society, and the insights they offer for human society. Finally, we discuss several key topics and open problems within the field. A repository for the related papers at https://github.com/WooooDyy/LLM-Agent-Paper-List.","external_url":"https://arxiv.org/abs/2309.07864","cited_by_count":1,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2309.07864","created_at":"2026-05-09T00:14:26.998678+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","render_title":"The Rise and Potential of Large Language Model Based Agents: A Survey"},"hub":{"state":{"work_id":"985ca219-7e34-4c4f-bdc5-ccd39763ad61","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":115,"external_cited_by_count":1,"distinct_field_count":18,"first_pith_cited_at":"2023-07-12T20:01:52+00:00","last_pith_cited_at":"2026-07-08T17:34:28+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T05:09:23.341497+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":26},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":26},{"context_polarity":"baseline","n":1},{"context_polarity":"use_method","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","claims":[{"claim_text":"For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"Evaluation of Retrieval-Augmented Generation: A Survey.CoRR abs/2405.07437 (2024). [181] Zichun Yu, Chenyan Xiong, Shi Yu, and Zhiyuan Liu. 2023. Augmentation- Adapted Retriever Improves Generalization of Language Models as Generic Plug- In. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL). 2421-2436. [182] Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yu","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"The advent of LLMs has significantly enhanced the capabili- ties of intelligent agents [43], enabling them to tackle complex tasks previously out of reach, particularly those involving natural language understanding and code generation [44]. This advancement has spurred substantial research into LLM- based agents designed for a wide array of applications [45]. Both Xie et al., [46] and Wang et al., [47] offer compre- hensive surveys on LLM-powered agents, covering essential background informatio","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Based on the capability of LLMs, people have conducted a lot of studies on building LLM-based agents, which can autonomously perceive environments, take actions, accumulate knowledge, and evolve themselves. In this field, Wang et al. [3] present the first survey paper to systematically summarize LLM-based agents from the perspectives of agent construction, agent application, and agent evaluation. Xi et al. [4], Zhao et al. [77], Cheng et al. [78] and Ge et al. [80] also summarize LLM-based agent","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Qin Liu, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, X. Huan, and Tao Gui. The Rise and Potential of Large Language Model Based Agents: A Survey.ArXiv, abs/2309.07864, sep 2023. [43] Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, D. Song, Huan Sun, and Yu Su. An Illusion of Progres","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"86%improvement over the second- best baseline.Notably, our 0.6B student achieves 26.13% on average@32 at AIME 2025, demonstrating effective transfer of agentic reasoning to lightweight models. Our code is available athttps://github.com/YoungZ365/SOD. 1 Introduction Agentic capabilities have substantially expanded the applicability of large language models (LLMs) [1, 2], enabling them to solve complex real-world tasks [3-5]. However, such capabilities are typically realized by large-scale models,","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"00515v2 [cs.CL] 10 Nov 2024 1:2 Juyong Jiang, Fan Wang, Jiasi Shen, Sungju Kim, and Sunghun Kim 1 INTRODUCTION The advent of Large Language Models (LLMs) such as ChatGPT1 [196] has profoundly transformed the landscape of automated code-related tasks [48], including code completion [87, 171, 270, 282], code translation [52, 135, 245], and code repair [75, 126, 195, 204, 291, 310]. A particularly intriguing application of LLMs is code generation, a task that involves producing source code from nat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks The Rise and Potential of Large Language Model Based Agents: A Survey because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (26 contexts).","role_counts":[{"n":26,"context_role":"background"},{"n":1,"context_role":"baseline"},{"n":1,"context_role":"method"}]},"error":null,"updated_at":"2026-07-03T08:23:44.469864+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"dc0dbeed-78a6-408e-8643-ae58086b137c","orcid":null,"display_name":"Zhiheng Xi"},{"id":"a07376d0-44b0-4141-b102-b7e028dd2d1e","orcid":null,"display_name":"Wenxiang Chen"},{"id":"32dcc396-7617-46e5-912a-160b2766475d","orcid":null,"display_name":"Xin Guo"},{"id":"00bd3e37-72fe-4b16-bca6-18686b5f7b7d","orcid":null,"display_name":"Wei He"},{"id":"d23331cc-5e4d-4d6a-88c1-261ec2c5519e","orcid":null,"display_name":"Yiwen Ding"},{"id":"f875f6b2-a4fb-4b3c-a495-729d01b8b44d","orcid":null,"display_name":"Boyang Hong"}]},"error":null,"updated_at":"2026-07-03T08:23:44.465242+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T16:52:47.637132+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":10},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":10},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":9},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":9},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":8},{"title":"Gorilla: Large Language Model Connected with Massive APIs","work_id":"126a464a-4a73-495f-b669-de1e44aa8f09","shared_citers":8},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":8},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"Code Llama: Open Foundation Models for Code","work_id":"e73bffa4-7620-47ac-9327-259a60db52ca","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":6},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":6},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":5},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":5},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":5},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":5},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":5},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":5},{"title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","work_id":"7b1b672f-e6b4-4df9-aa8b-3396a2eb8b16","shared_citers":4},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":4}],"time_series":[{"n":4,"year":2024},{"n":2,"year":2025},{"n":38,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T16:52:53.055030+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T16:52:50.289227+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","claims":[{"claim_text":"For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"Evaluation of Retrieval-Augmented Generation: A Survey.CoRR abs/2405.07437 (2024). [181] Zichun Yu, Chenyan Xiong, Shi Yu, and Zhiyuan Liu. 2023. Augmentation- Adapted Retriever Improves Generalization of Language Models as Generic Plug- In. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL). 2421-2436. [182] Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yu","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"The advent of LLMs has significantly enhanced the capabili- ties of intelligent agents [43], enabling them to tackle complex tasks previously out of reach, particularly those involving natural language understanding and code generation [44]. This advancement has spurred substantial research into LLM- based agents designed for a wide array of applications [45]. Both Xie et al., [46] and Wang et al., [47] offer compre- hensive surveys on LLM-powered agents, covering essential background informatio","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Based on the capability of LLMs, people have conducted a lot of studies on building LLM-based agents, which can autonomously perceive environments, take actions, accumulate knowledge, and evolve themselves. In this field, Wang et al. [3] present the first survey paper to systematically summarize LLM-based agents from the perspectives of agent construction, agent application, and agent evaluation. Xi et al. [4], Zhao et al. [77], Cheng et al. [78] and Ge et al. [80] also summarize LLM-based agent","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Qin Liu, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, X. Huan, and Tao Gui. The Rise and Potential of Large Language Model Based Agents: A Survey.ArXiv, abs/2309.07864, sep 2023. [43] Tianci Xue, Weijian Qi, Tianneng Shi, Chan Hee Song, Boyu Gou, D. Song, Huan Sun, and Yu Su. An Illusion of Progres","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"86%improvement over the second- best baseline.Notably, our 0.6B student achieves 26.13% on average@32 at AIME 2025, demonstrating effective transfer of agentic reasoning to lightweight models. Our code is available athttps://github.com/YoungZ365/SOD. 1 Introduction Agentic capabilities have substantially expanded the applicability of large language models (LLMs) [1, 2], enabling them to solve complex real-world tasks [3-5]. However, such capabilities are typically realized by large-scale models,","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"00515v2 [cs.CL] 10 Nov 2024 1:2 Juyong Jiang, Fan Wang, Jiasi Shen, Sungju Kim, and Sunghun Kim 1 INTRODUCTION The advent of Large Language Models (LLMs) such as ChatGPT1 [196] has profoundly transformed the landscape of automated code-related tasks [48], including code completion [87, 171, 270, 282], code translation [52, 135, 245], and code repair [75, 126, 195, 204, 291, 310]. A particularly intriguing application of LLMs is code generation, a task that involves producing source code from nat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks The Rise and Potential of Large Language Model Based Agents: A Survey because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (26 contexts).","role_counts":[{"n":26,"context_role":"background"},{"n":1,"context_role":"baseline"},{"n":1,"context_role":"method"}]},"error":null,"updated_at":"2026-07-03T08:23:43.427984+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","claims":[{"claim_text":"For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks The Rise and Potential of Large Language Model Based Agents: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T16:52:40.889238+00:00"}},"summary":{"title":"The Rise and Potential of Large Language Model Based Agents: A Survey","claims":[{"claim_text":"For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are artificial entities that sense their environment, make decisions, and take actions. Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks. Actually, what the community lacks is a general and powerful model to serve as a starting point for designing AI agents that","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks The Rise and Potential of Large Language Model Based Agents: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":10},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":10},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":9},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":9},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":8},{"title":"Gorilla: Large Language Model Connected with Massive APIs","work_id":"126a464a-4a73-495f-b669-de1e44aa8f09","shared_citers":8},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":8},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"Code Llama: Open Foundation Models for Code","work_id":"e73bffa4-7620-47ac-9327-259a60db52ca","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":6},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":6},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":6},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":5},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":5},{"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","shared_citers":5},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":5},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":5},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":5},{"title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","work_id":"7b1b672f-e6b4-4df9-aa8b-3396a2eb8b16","shared_citers":4},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":4}],"time_series":[{"n":4,"year":2024},{"n":2,"year":2025},{"n":38,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"f875f6b2-a4fb-4b3c-a495-729d01b8b44d","orcid":null,"display_name":"Boyang Hong","source":"manual","import_confidence":0.72},{"id":"00bd3e37-72fe-4b16-bca6-18686b5f7b7d","orcid":null,"display_name":"Wei He","source":"manual","import_confidence":0.72},{"id":"a07376d0-44b0-4141-b102-b7e028dd2d1e","orcid":null,"display_name":"Wenxiang Chen","source":"manual","import_confidence":0.72},{"id":"32dcc396-7617-46e5-912a-160b2766475d","orcid":null,"display_name":"Xin Guo","source":"manual","import_confidence":0.72},{"id":"d23331cc-5e4d-4d6a-88c1-261ec2c5519e","orcid":null,"display_name":"Yiwen Ding","source":"manual","import_confidence":0.72},{"id":"dc0dbeed-78a6-408e-8643-ae58086b137c","orcid":null,"display_name":"Zhiheng Xi","source":"manual","import_confidence":0.72}]}}