{"work":{"id":"778f739e-5f55-4961-8a2a-e4736a2757f4","openalex_id":null,"doi":null,"arxiv_id":"2303.11366","raw_key":null,"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","authors":null,"authors_text":"Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao","year":2023,"venue":"cs.AI","abstract":"Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain their own reflective text in an episodic memory buffer to induce better decision-making in subsequent trials. Reflexion is flexible enough to incorporate various types (scalar values or free-form language) and sources (external or internally simulated) of feedback signals, and obtains significant improvements over a baseline agent across diverse tasks (sequential decision-making, coding, language reasoning). For example, Reflexion achieves a 91% pass@1 accuracy on the HumanEval coding benchmark, surpassing the previous state-of-the-art GPT-4 that achieves 80%. We also conduct ablation and analysis studies using different feedback signals, feedback incorporation methods, and agent types, and provide insights into how they affect performance.","external_url":"https://arxiv.org/abs/2303.11366","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T07:15:27.753979+00:00","pith_arxiv_id":"2303.11366","created_at":"2026-05-09T05:50:26.094618+00:00","updated_at":"2026-05-25T07:15:27.753979+00:00","title_quality_ok":true,"display_title":"Reflexion: Language Agents with Verbal Reinforcement Learning","render_title":"Reflexion: Language Agents with Verbal Reinforcement Learning"},"hub":{"state":{"work_id":"778f739e-5f55-4961-8a2a-e4736a2757f4","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":142,"external_cited_by_count":null,"distinct_field_count":14,"first_pith_cited_at":"2023-02-03T06:06:27+00:00","last_pith_cited_at":"2026-05-22T00:05:36+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":"2026-06-05T07:28:43.108373+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":36},{"context_role":"method","n":7},{"context_role":"baseline","n":2},{"context_role":"dataset","n":2}],"polarity_counts":[{"context_polarity":"background","n":32},{"context_polarity":"use_method","n":7},{"context_polarity":"support","n":3},{"context_polarity":"baseline","n":2},{"context_polarity":"use_dataset","n":2},{"context_polarity":"unclear","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","claims":[{"claim_text":"Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain the","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"to mitigate SHADOWMERGE. We have responsibly disclosed our findings to affected graph-memory vendors and open sourced SHADOWMERGE at https://anonymous.4open.science/status/S hadowMerge -033C. I. INTRODUCTION LLM agents are moving from single-turn chatbots [1], [2] toward long-running systems that remember, adapt, and act across repeated interactions [3], [4], [5]. Persistent mem- ory [6], [7], [8], [9], [10] enables this shift by allowing agents to reuse past tool outcomes, maintain user prefere","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face.Advances in Neural Information Processing Systems, 36, 2023. [26] Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection.arXiv preprint, abs/2303.11366, 2023. doi: 10.48550/ arXiv.2303.11366. URLhttps://doi.org/10.48550/arXiv.2303.11366. [27] Yifan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian, Mingbo Song, Hailiang Huang, Cheng Li, Ke Wang, Rong Yao, Ye Ti","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the next milestone (Fig. 2). Empirically, VOYAGER demonstrates strong in-context lifelong learningcapabilities. It can construct an ever-growing skill library of action programs that are reusable, interpretable, and generalizable to novel tasks. We evaluate VOYAGER systematically against other LLM-based agent techniques (e.g., ReAct [29], Reflexion [30], AutoGPT [28]) in MineDojo [23], an open-source Minecraft AI framework. VOYAGER outperforms prior SOTA by obtaining3.3× more unique items, unloc","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[159], etc. Mitigate hallucination Manakul et al. [160], Qin et al. [94], Li et al. [161], Gou et al. [162], etc. Memory §3.1.3 Memory capability Raising the length limit of Transformers BART [163], Park et al. [164], LongT5 [165], CoLT5 [166], Ruoss et al. [167], etc. Summarizing memory Generative Agents [22], SCM [168], Reflexion [169], Memory- bank [170], ChatEval [171], etc. Compressing mem- ories with vectors or data structures ChatDev [109], GITM [172], RET-LLM [173], AgentSims [174], Chat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"focuses on accurate project localization, such as identifying relevant files and functions for issue resolution, a critical first step in software maintenance. We split the 36 repositories by domain, using a subset of domains for skill evolution and validation and reserving the remaining repositories for testing. For text-based household-agent tasks, we use ALFWorld [18], where the training split is used to construct the evolution and validation sets and the valid-seen split is used as the test ","claim_type":"dataset","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"semantic matching with topological graph expansion to ensure logical completeness and suppress hallucinations [14-16]. By enforcing structural constraints, this mechanism suppresses hallucinations and satisfies the reliability requirements of industrial assembly. The LineBalanceAgent optimizes process allocation via a natural-language-driven self-reflective strategy [17], while the scene graph maintains a structured spatial-resource representation. Following the ReAct-based reasoning paradigm [1","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Reflexion: Language Agents with Verbal Reinforcement Learning because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (13 contexts).","role_counts":[{"n":13,"context_role":"background"},{"n":5,"context_role":"method"},{"n":1,"context_role":"baseline"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-17T05:29:33.111306+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"2e4e9c2a-3fa8-4dbc-bfaf-de575a854051","orcid":null,"display_name":"Noah Shinn"},{"id":"99eeeb7a-c66e-494e-9322-87da7697a8f0","orcid":null,"display_name":"Federico Cassano"},{"id":"15383fe9-133a-4524-8d3b-82813a6814d6","orcid":null,"display_name":"Edward Berman"},{"id":"8e24f29a-9775-494b-8798-74a5b6121830","orcid":null,"display_name":"Ashwin Gopinath"},{"id":"100cd29d-0db3-4c66-b69f-fd6ae13c609a","orcid":null,"display_name":"Karthik Narasimhan"},{"id":"55ffc739-fb29-4c94-90fd-a74183bd62cf","orcid":null,"display_name":"Shunyu Yao"}]},"error":null,"updated_at":"2026-05-17T05:29:33.804483+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T06:57:36.804764+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":25},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":25},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":18},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":16},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":16},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":15},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":14},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":14},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":14},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":13},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":11},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":10},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":9},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":8},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":8},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":7},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":7},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":7},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":7}],"time_series":[{"n":9,"year":2023},{"n":2,"year":2024},{"n":69,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T07:07:25.905281+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":"2026-05-14T06:57:28.630506+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","claims":[{"claim_text":"Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain the","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"to mitigate SHADOWMERGE. We have responsibly disclosed our findings to affected graph-memory vendors and open sourced SHADOWMERGE at https://anonymous.4open.science/status/S hadowMerge -033C. I. INTRODUCTION LLM agents are moving from single-turn chatbots [1], [2] toward long-running systems that remember, adapt, and act across repeated interactions [3], [4], [5]. Persistent mem- ory [6], [7], [8], [9], [10] enables this shift by allowing agents to reuse past tool outcomes, maintain user prefere","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face.Advances in Neural Information Processing Systems, 36, 2023. [26] Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection.arXiv preprint, abs/2303.11366, 2023. doi: 10.48550/ arXiv.2303.11366. URLhttps://doi.org/10.48550/arXiv.2303.11366. [27] Yifan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian, Mingbo Song, Hailiang Huang, Cheng Li, Ke Wang, Rong Yao, Ye Ti","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"the next milestone (Fig. 2). Empirically, VOYAGER demonstrates strong in-context lifelong learningcapabilities. It can construct an ever-growing skill library of action programs that are reusable, interpretable, and generalizable to novel tasks. We evaluate VOYAGER systematically against other LLM-based agent techniques (e.g., ReAct [29], Reflexion [30], AutoGPT [28]) in MineDojo [23], an open-source Minecraft AI framework. VOYAGER outperforms prior SOTA by obtaining3.3× more unique items, unloc","claim_type":"baseline","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"[159], etc. Mitigate hallucination Manakul et al. [160], Qin et al. [94], Li et al. [161], Gou et al. [162], etc. Memory §3.1.3 Memory capability Raising the length limit of Transformers BART [163], Park et al. [164], LongT5 [165], CoLT5 [166], Ruoss et al. [167], etc. Summarizing memory Generative Agents [22], SCM [168], Reflexion [169], Memory- bank [170], ChatEval [171], etc. Compressing mem- ories with vectors or data structures ChatDev [109], GITM [172], RET-LLM [173], AgentSims [174], Chat","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"focuses on accurate project localization, such as identifying relevant files and functions for issue resolution, a critical first step in software maintenance. We split the 36 repositories by domain, using a subset of domains for skill evolution and validation and reserving the remaining repositories for testing. For text-based household-agent tasks, we use ALFWorld [18], where the training split is used to construct the evolution and validation sets and the valid-seen split is used as the test ","claim_type":"dataset","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"semantic matching with topological graph expansion to ensure logical completeness and suppress hallucinations [14-16]. By enforcing structural constraints, this mechanism suppresses hallucinations and satisfies the reliability requirements of industrial assembly. The LineBalanceAgent optimizes process allocation via a natural-language-driven self-reflective strategy [17], while the scene graph maintains a structured spatial-resource representation. Following the ReAct-based reasoning paradigm [1","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Reflexion: Language Agents with Verbal Reinforcement Learning because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (13 contexts).","role_counts":[{"n":13,"context_role":"background"},{"n":5,"context_role":"method"},{"n":1,"context_role":"baseline"},{"n":1,"context_role":"dataset"}]},"error":null,"updated_at":"2026-05-17T05:29:33.107187+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","claims":[{"claim_text":"Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain the","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Reflexion: Language Agents with Verbal Reinforcement Learning because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T07:07:27.965753+00:00"}},"summary":{"title":"Reflexion: Language Agents with Verbal Reinforcement Learning","claims":[{"claim_text":"Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn from trial-and-error as traditional reinforcement learning methods require extensive training samples and expensive model fine-tuning. We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback. Concretely, Reflexion agents verbally reflect on task feedback signals, then maintain the","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Reflexion: Language Agents with Verbal Reinforcement Learning because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":25},{"title":"Self-Refine: Iterative Refinement with Self-Feedback","work_id":"59181e7f-e58e-45d3-8146-4477a9f53d5a","shared_citers":25},{"title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","work_id":"d1cf6693-a082-403c-ada9-dac7b96341f9","shared_citers":18},{"title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","work_id":"ffe0d207-86cf-4742-a100-e988ac8b9676","shared_citers":18},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":16},{"title":"Toolformer: Language Models Can Teach Themselves to Use Tools","work_id":"9bce40c8-cfd7-4983-80e0-c3bd4402322a","shared_citers":16},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":15},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":14},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":14},{"title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","work_id":"07adb06e-4ed5-4ec5-a7ae-ff288fd214fb","shared_citers":14},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":13},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":12},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":11},{"title":"Training language models to follow instructions with human feedback","work_id":"52aff42f-4fa9-4fcf-bdb3-1459b9bebf65","shared_citers":11},{"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","shared_citers":10},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":9},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":8},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":8},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":7},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":7},{"title":"Generative Agents: Interactive Simulacra of Human Behavior","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","shared_citers":7},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":7},{"title":"WebGPT: Browser-assisted question-answering with human feedback","work_id":"e25ef3e1-4848-4cb9-bf28-67a420591165","shared_citers":7}],"time_series":[{"n":9,"year":2023},{"n":2,"year":2024},{"n":69,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"8e24f29a-9775-494b-8798-74a5b6121830","orcid":null,"display_name":"Ashwin Gopinath","source":"manual","import_confidence":0.72},{"id":"15383fe9-133a-4524-8d3b-82813a6814d6","orcid":null,"display_name":"Edward Berman","source":"manual","import_confidence":0.72},{"id":"99eeeb7a-c66e-494e-9322-87da7697a8f0","orcid":null,"display_name":"Federico Cassano","source":"manual","import_confidence":0.72},{"id":"100cd29d-0db3-4c66-b69f-fd6ae13c609a","orcid":null,"display_name":"Karthik Narasimhan","source":"manual","import_confidence":0.72},{"id":"2e4e9c2a-3fa8-4dbc-bfaf-de575a854051","orcid":null,"display_name":"Noah Shinn","source":"manual","import_confidence":0.72},{"id":"55ffc739-fb29-4c94-90fd-a74183bd62cf","orcid":null,"display_name":"Shunyu Yao","source":"manual","import_confidence":0.72}]}}