{"work":{"id":"891b9780-a800-4e3c-bba0-53597ab8dc98","openalex_id":null,"doi":null,"arxiv_id":"2308.00352","raw_key":null,"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","authors":null,"authors_text":"Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang","year":2023,"venue":"cs.AI","abstract":"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT","external_url":"https://arxiv.org/abs/2308.00352","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-06-29T12:03:23.958242+00:00","pith_arxiv_id":"2308.00352","created_at":"2026-05-10T00:19:46.702275+00:00","updated_at":"2026-06-29T12:03:23.958242+00:00","title_quality_ok":true,"display_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","render_title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework"},"hub":{"state":{"work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":120,"external_cited_by_count":null,"distinct_field_count":18,"first_pith_cited_at":"2023-07-12T20:01:52+00:00","last_pith_cited_at":"2026-06-08T19:35:37+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":"2026-06-29T11:58:42.071838+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":35},{"context_role":"method","n":2},{"context_role":"dataset","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":36},{"context_polarity":"unclear","n":1},{"context_polarity":"use_dataset","n":1},{"context_polarity":"use_method","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","claims":[{"claim_text":"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for mor","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"MPC [101] ✓ × × Generative Agents [83] ✓ × × RecMind [102] ✓ × ✓ Retroformer [103] ✓ ✓ ✓ ExpeL [82] ✓ ✓ ✓ Synapse [91] ✓ ✓ × GITM [93] ✓ ✓ ✓ ReAct [104] ✓ × ✓ Reflexion [5] ✓ ✓ ✓ RecAgent [95] ✓ × × Character-LLM [105] ✓ × ✓ MAC [106] ✓ × × Huatuo [107] ✓ × ✓ ChatDev [1] ✓ × × InteRecAgent [108] ✓ × ✓ MetaAgents [109] ✓ × × TPTU [110, 111] ✓ × ✓ MetaGPT [112] ✓ ✓ × S3 [2] ✓ × × InvestLM [113] ✓ × ✓ generated in the agent-environment interaction process (e.g., task internal information), while th","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"quantization-quantize the quantization constants them- selves to save memory; (2)paged optimizers-offload op- timizer states to CPU RAM via unified memory. Trade- offs: QLoRA introduces≈10% training slowdown (de- quantization overhead) but enables 4×larger models on given hardware. Quality degradation is ¡2% on standard benchmarks when using NF4 vs FP16 base model. Adapter Layers[68] insert bottleneck feed-forward modules between Transformer layers:h ′ =h+ f(hW down)Wup whereW down ∈R d×r projec","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the items current models most frequently miss [16]; our empirically-hardest-100 construction (section 4.3) adopts this idea. 2.3 LLM-as-Judge Evaluation The LLM-as-judge paradigm was popularized by Zheng et al. [25] (MT-Bench and Chatbot Arena), who demonstrated that capable LLMs, particularly GPT-4, can approximate human preference scoring on open-ended tasks at above 80% agreement. Kim et al. [13] trained Prometheus, an open-source 13-billion-parameter fine-tuned evaluator LLM, to produce fine","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"tures, small language models for agentic workloads, RL for multi-turn LLM-based agents and LLM-judge / rubric-based reward design. We discuss each below. 2.1 Multi-Agent and Subagent Architectures Decomposing complex tasks across multiple agents has been studied extensively. AutoGen [11] provides a flexible frame- work for agent to agent conversation. Works like MetaGPT [12], ChatDev [13], explore role-based collaboration between mul- tiple agents. He et al. [14] systematically reviewed the land","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"and recover from agent misbehavior independent of the under- lying LLM's alignment. 2.1 Soft Constraints Are Not Governance AutoGen [3] provides flexible multi-agent conversation patterns with customizable termination conditions. CrewAI [5] for- malizes role-based task decomposition with configurable del- egation. LangGraph [6] enables graph-based agent orchestra- tion with conditional routing. MetaGPT [4] and ChatDev [7] demonstrate impressive role-playing for software engineering. These are ex","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"serves typed intermediate artifacts, allows explicit supersession, and keeps downstream dependencies addressable. 3 Background and Related Work 3.1 Agent Loops, Tool Use, and Intermediate Reasoning Agentic LLM systems commonly interleave reasoning, tool use, and revision inside iterative loops. ReAct [1] remains the canonical example of this paradigm, while Toolformer [2], AutoGen [6], CAMEL [3], V oyager [4], and MetaGPT [5] explore richer tool ecosystems, role structures, and multi-agent coord","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (32 contexts).","role_counts":[{"n":32,"context_role":"background"},{"n":2,"context_role":"method"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-20T13:52:00.176473+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"f90f7b62-d401-4dc1-aa60-ad04864f651c","orcid":null,"display_name":"Sirui Hong"},{"id":"f82dff1a-1631-4b05-9808-50e6ca97d03e","orcid":null,"display_name":"Mingchen Zhuge"},{"id":"f05d07d6-b44c-436d-8bb2-7403f8b512cc","orcid":null,"display_name":"Jiaqi Chen"},{"id":"9c8261e2-037e-4374-8849-f8274619e092","orcid":null,"display_name":"Xiawu Zheng"},{"id":"b1f08c01-f549-44cd-bf95-900f4929aa63","orcid":null,"display_name":"Yuheng Cheng"},{"id":"91dfab81-dd8f-4f99-943a-555516e76fc3","orcid":null,"display_name":"Ceyao Zhang"}]},"error":null,"updated_at":"2026-05-20T13:52:00.171634+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T10:39:22.153726+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":36},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":14},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":12},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":11},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":11},{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","work_id":"ba431bb8-7f34-4a9e-9b03-51585294d7d3","shared_citers":10},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":9},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":8},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":8},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":7},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":7},{"title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","work_id":"01826cd9-a652-403c-a2ec-531da9fe2b6a","shared_citers":7},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":7},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":7},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":7},{"title":"AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors","work_id":"3187ed22-d803-437a-88c1-abab6eeb2af6","shared_citers":6},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":6},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":6},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":6},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":5},{"title":"Gorilla: Large Language Model Connected with Massive APIs","work_id":"126a464a-4a73-495f-b669-de1e44aa8f09","shared_citers":5}],"time_series":[{"n":1,"year":2023},{"n":2,"year":2024},{"n":1,"year":2025},{"n":58,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T10:49:15.030008+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":"2026-05-14T10:39:24.435654+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","claims":[{"claim_text":"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for mor","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"MPC [101] ✓ × × Generative Agents [83] ✓ × × RecMind [102] ✓ × ✓ Retroformer [103] ✓ ✓ ✓ ExpeL [82] ✓ ✓ ✓ Synapse [91] ✓ ✓ × GITM [93] ✓ ✓ ✓ ReAct [104] ✓ × ✓ Reflexion [5] ✓ ✓ ✓ RecAgent [95] ✓ × × Character-LLM [105] ✓ × ✓ MAC [106] ✓ × × Huatuo [107] ✓ × ✓ ChatDev [1] ✓ × × InteRecAgent [108] ✓ × ✓ MetaAgents [109] ✓ × × TPTU [110, 111] ✓ × ✓ MetaGPT [112] ✓ ✓ × S3 [2] ✓ × × InvestLM [113] ✓ × ✓ generated in the agent-environment interaction process (e.g., task internal information), while th","claim_type":"background","confidence":0.95,"evidence_strength":"citation_context"},{"claim_text":"quantization-quantize the quantization constants them- selves to save memory; (2)paged optimizers-offload op- timizer states to CPU RAM via unified memory. Trade- offs: QLoRA introduces≈10% training slowdown (de- quantization overhead) but enables 4×larger models on given hardware. Quality degradation is ¡2% on standard benchmarks when using NF4 vs FP16 base model. Adapter Layers[68] insert bottleneck feed-forward modules between Transformer layers:h ′ =h+ f(hW down)Wup whereW down ∈R d×r projec","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the items current models most frequently miss [16]; our empirically-hardest-100 construction (section 4.3) adopts this idea. 2.3 LLM-as-Judge Evaluation The LLM-as-judge paradigm was popularized by Zheng et al. [25] (MT-Bench and Chatbot Arena), who demonstrated that capable LLMs, particularly GPT-4, can approximate human preference scoring on open-ended tasks at above 80% agreement. Kim et al. [13] trained Prometheus, an open-source 13-billion-parameter fine-tuned evaluator LLM, to produce fine","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"tures, small language models for agentic workloads, RL for multi-turn LLM-based agents and LLM-judge / rubric-based reward design. We discuss each below. 2.1 Multi-Agent and Subagent Architectures Decomposing complex tasks across multiple agents has been studied extensively. AutoGen [11] provides a flexible frame- work for agent to agent conversation. Works like MetaGPT [12], ChatDev [13], explore role-based collaboration between mul- tiple agents. He et al. [14] systematically reviewed the land","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"and recover from agent misbehavior independent of the under- lying LLM's alignment. 2.1 Soft Constraints Are Not Governance AutoGen [3] provides flexible multi-agent conversation patterns with customizable termination conditions. CrewAI [5] for- malizes role-based task decomposition with configurable del- egation. LangGraph [6] enables graph-based agent orchestra- tion with conditional routing. MetaGPT [4] and ChatDev [7] demonstrate impressive role-playing for software engineering. These are ex","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"serves typed intermediate artifacts, allows explicit supersession, and keeps downstream dependencies addressable. 3 Background and Related Work 3.1 Agent Loops, Tool Use, and Intermediate Reasoning Agentic LLM systems commonly interleave reasoning, tool use, and revision inside iterative loops. ReAct [1] remains the canonical example of this paradigm, while Toolformer [2], AutoGen [6], CAMEL [3], V oyager [4], and MetaGPT [5] explore richer tool ecosystems, role structures, and multi-agent coord","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (32 contexts).","role_counts":[{"n":32,"context_role":"background"},{"n":2,"context_role":"method"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-20T13:51:59.735468+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","claims":[{"claim_text":"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for mor","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T10:49:15.035310+00:00"}},"summary":{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","claims":[{"claim_text":"Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for mor","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework 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":36},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":14},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":12},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":11},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":11},{"title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","work_id":"ba431bb8-7f34-4a9e-9b03-51585294d7d3","shared_citers":10},{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","shared_citers":9},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":8},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":8},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":7},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":7},{"title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","work_id":"01826cd9-a652-403c-a2ec-531da9fe2b6a","shared_citers":7},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":7},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":7},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":7},{"title":"AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors","work_id":"3187ed22-d803-437a-88c1-abab6eeb2af6","shared_citers":6},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":6},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":6},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":6},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":6},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":6},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":5},{"title":"Gorilla: Large Language Model Connected with Massive APIs","work_id":"126a464a-4a73-495f-b669-de1e44aa8f09","shared_citers":5}],"time_series":[{"n":1,"year":2023},{"n":2,"year":2024},{"n":1,"year":2025},{"n":58,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"91dfab81-dd8f-4f99-943a-555516e76fc3","orcid":null,"display_name":"Ceyao Zhang","source":"manual","import_confidence":0.72},{"id":"f05d07d6-b44c-436d-8bb2-7403f8b512cc","orcid":null,"display_name":"Jiaqi Chen","source":"manual","import_confidence":0.72},{"id":"f82dff1a-1631-4b05-9808-50e6ca97d03e","orcid":null,"display_name":"Mingchen Zhuge","source":"manual","import_confidence":0.72},{"id":"f90f7b62-d401-4dc1-aa60-ad04864f651c","orcid":null,"display_name":"Sirui Hong","source":"manual","import_confidence":0.72},{"id":"9c8261e2-037e-4374-8849-f8274619e092","orcid":null,"display_name":"Xiawu Zheng","source":"manual","import_confidence":0.72},{"id":"b1f08c01-f549-44cd-bf95-900f4929aa63","orcid":null,"display_name":"Yuheng Cheng","source":"manual","import_confidence":0.72}]}}