{"work":{"id":"9074870f-aee7-4103-b167-ac6473a8a9b3","openalex_id":"https://openalex.org/W4403571340","doi":"10.48550/arxiv.2410.10813","arxiv_id":"2410.10813","raw_key":null,"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","authors":null,"authors_text":"Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, Dong Yu","year":2024,"venue":"cs.CL","abstract":"Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assistant chat histories, LongMemEval presents a significant challenge to existing long-term memory systems, with commercial chat assistants and long-context LLMs showing a 30% accuracy drop on memorizing information across sustained interactions. We then present a unified framework that breaks down the long-term memory design into three stages: indexing, retrieval, and reading. Built upon key experimental insights, we propose several memory design optimizations including session decomposition for value granularity, fact-augmented key expansion for indexing, and time-aware query expansion for refining the search scope. Extensive experiments show that these optimizations greatly improve both memory recall and downstream question answering on LongMemEval. Overall, our study provides valuable resources and guidance for advancing the long-term memory capabilities of LLM-based chat assistants, paving the way toward more personalized and reliable conversational AI. Our benchmark and code are publicly available at https://github.com/xiaowu0162/LongMemEval.","external_url":"https://arxiv.org/abs/2410.10813","cited_by_count":3,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2410.10813","created_at":"2026-05-09T04:50:13.392200+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","render_title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory"},"hub":{"state":{"work_id":"9074870f-aee7-4103-b167-ac6473a8a9b3","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":114,"external_cited_by_count":3,"distinct_field_count":8,"first_pith_cited_at":"2025-02-20T15:32:24+00:00","last_pith_cited_at":"2026-07-09T01:15:03+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":"2026-08-21T15:49:26.603412+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":6},{"context_role":"dataset","n":3},{"context_role":"baseline","n":2},{"context_role":"method","n":2}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_dataset","n":3},{"context_polarity":"baseline","n":2},{"context_polarity":"use_method","n":2},{"context_polarity":"support","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","claims":[{"claim_text":"Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assista","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"For example, a hospital may publish de-identified diagnostic records for remote triage agents, with every call validated for context and provenance. 6 Evaluation To systematically evaluate the capabilities ofMemOS, we conduct both holistic and component-level experi- ments. We begin by benchmarking the full system on the LoCoMo [100], LongMemEval [101], PreFEval [102] and PersonaMem [103] benchmark suite to assess its performance in memory-intensive reasoning and personal- ization tasks, compari","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"How to make our ideas clear. Popular Science Monthly , 12, 286-302. [35] Planck, M. (1950). Scientific Autobiography and Other Papers . Williams & Norgate. [36] Qian, C., Parisi, A., Bouleau, C., Tsai, V., Lebreton, M., & Dixon, L. (2025). To mask or to mirror: Human-AI alignment in collective reasoning. In Proceedings of EMNLP 2025 . arXiv:2510.01924. [37] Shi, W., Gao, M., Xu, Z., Feng, S., Xu, W., Shi, P., Zettlemoyer, L., & Tsvetkov, Y. (2024). LongMemEval: Benchmarking chat assistants on lo","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"gains under the same runtime budget, supporting the principle that memory should preserve the distinctions that matter for decisions, not descriptions. 1 Introduction Large language model (LLM) agents increasingly operate over long interaction horizons. They must answer using earlier dialogue, plan from past observations, and adapt behavior using feedback accumulated across trials and sessions [43, 34]. Yet long-horizon interaction remains bottlenecked by memory. Increasing the context window al","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"These results suggest that structured intent routing and deterministic evidence preparation can make limited-capacity models substantially more effective in resource-constrained long-horizon agents. 1 Introduction Language agents operating over long-horizon interactions must answer queries whose evidence spans many turns, sessions, and topic shifts [43, 25, 30, 32]. The common strategy of appending the full history causes unbounded memory growth, high cost, and degraded reasoning once inputs exc","claim_type":"dataset","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"FILCO [176]; Provence [23]; DSLR [65]; Adaptive-RAG [69] LLMLingua [70]; LongLLMLingua [71]; LLMLingua-2 [130]; RECOMP [189]; Compression for RAG [91]; Gist Tokens [119]; ICAE [45]; xRAG [22]; Token-efficiency objective [190] Lost in the Middle [100]; Topology-aware ordering [136]; OP-RAG [197]; Irrelevant-context robust- ness [151] Conflict-aware assembly [170, 187]; Chain-of-Note [199]; Astute RAG [169]; Conflict diagnostics [15, 98]; OpenDecoder [118] Fine-grained Attribution Safety Evaluatio","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"such as Healthcare Agent [26], LD-Agent [18], and AMDS [36] demonstrate the promise of LLMs in healthcare, but they generally treat memory as a static component rather than a long-horizon, continuously updated system. Agent Memory Benchmarks.Existing benchmarks are largely eitherdialogue-centricorlong-context. Dialogue- centric benchmarks, such as LoCoMo [ 21], LongMemEval [ 34], MemoryAgentBench [ 14], HaluMem [ 4], and AMA-Bench [42], evaluate conversational memory, memory operations, or agent","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (6 contexts).","role_counts":[{"n":6,"context_role":"background"},{"n":3,"context_role":"dataset"},{"n":2,"context_role":"baseline"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-07-03T10:54:03.680436+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"86061020-1af4-475c-b28f-4eea64bf86ba","orcid":null,"display_name":"Di Wu"},{"id":"06e04a2b-a439-46c8-ad92-ec459ac7b693","orcid":null,"display_name":"Hongwei Wang"},{"id":"4249b1a9-b59a-4bb1-bd2a-eb7e0cfebb9b","orcid":null,"display_name":"Wenhao Yu"},{"id":"f97ef65b-7941-4af2-ab5f-2eb38cdabe9c","orcid":null,"display_name":"Yuwei Zhang"},{"id":"83d1a88e-067b-4af3-a79e-df5e6a06a84e","orcid":null,"display_name":"Kai-Wei Chang"},{"id":"0e65188c-1a9d-4ee4-b5e2-248f93ab1083","orcid":null,"display_name":"Dong Yu"}]},"error":null,"updated_at":"2026-07-03T10:54:03.678110+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:19:46.500762+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":21},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":16},{"title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","work_id":"2d8c9fb7-9ace-4925-8fe1-f4e44625d04c","shared_citers":15},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":15},{"title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","work_id":"515c933e-12ae-439d-a7ff-c07fee482dfb","shared_citers":12},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":10},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":9},{"title":"Memory in the Age of AI Agents","work_id":"1ff75a14-302e-4906-aa86-1f96fbcf12ff","shared_citers":8},{"title":"Evaluating memory in llm agents via incremental multi-turn interactions","work_id":"df5096c3-e738-472b-953c-fb510ee9e68d","shared_citers":7},{"title":"Ama-bench: Evaluating long-horizon memory for agentic applications","work_id":"511e9b37-73a4-4ced-9b91-1bc2798c3c5c","shared_citers":6},{"title":"arXiv:2405.14831 [cs.CL] https://arxiv.org/abs/2405.14831","work_id":"c964b1e8-cbf5-49dd-ac34-b8f733b02a9d","shared_citers":5},{"title":"Evaluating very long-term conversational memory of LLM agents","work_id":"6bbf9aa9-b06f-489e-8977-aeb1261f2ef8","shared_citers":5},{"title":"Memorybank: Enhancing large language models with long-term memory","work_id":"3f0e5fbe-8eb1-48c4-9e30-cf41428c3046","shared_citers":5},{"title":"Memos: A memory os for ai system","work_id":"e686f058-6c5c-4484-a88e-26d945657ed3","shared_citers":5},{"title":"Mirix: Multi-agent memory system for llm-based agents","work_id":"bcb99885-6f76-4bd6-b442-e5f455bb6447","shared_citers":5},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":5},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":5},{"title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","work_id":"4519e90e-26c9-43ef-a89b-c8e8a8378280","shared_citers":4},{"title":"Bernstein","work_id":"b5bf85fe-4fb7-4966-b0b2-9ccf9d3b11b9","shared_citers":4},{"title":"From human memory to ai memory: A survey on memory mechanisms in the era of llms.arXiv preprint arXiv:2504.15965","work_id":"56f08885-28c9-4956-88e1-91190c6ca650","shared_citers":4},{"title":"MEM1: learning to synergize memory and reasoning for efficient long-horizon agents.CoRR, abs/2506.15841","work_id":"43cfa793-fb98-4501-8224-4dfb9e56285c","shared_citers":4},{"title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","work_id":"2a070440-2167-4398-be97-c2d4c3ee3541","shared_citers":4},{"title":"Memos: An operating system for memory-augmented generation (mag) in large language models","work_id":"62f802d2-2c22-4140-9b3d-b8b7220f772e","shared_citers":4},{"title":"my old area","work_id":"43456f70-b374-4adb-97b5-6ec329c73793","shared_citers":4}],"time_series":[{"n":32,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:20:13.284936+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":"2026-05-14T18:19:51.538758+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","claims":[{"claim_text":"Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assista","claim_type":"abstract","evidence_strength":"source_metadata"},{"claim_text":"For example, a hospital may publish de-identified diagnostic records for remote triage agents, with every call validated for context and provenance. 6 Evaluation To systematically evaluate the capabilities ofMemOS, we conduct both holistic and component-level experi- ments. We begin by benchmarking the full system on the LoCoMo [100], LongMemEval [101], PreFEval [102] and PersonaMem [103] benchmark suite to assess its performance in memory-intensive reasoning and personal- ization tasks, compari","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"How to make our ideas clear. Popular Science Monthly , 12, 286-302. [35] Planck, M. (1950). Scientific Autobiography and Other Papers . Williams & Norgate. [36] Qian, C., Parisi, A., Bouleau, C., Tsai, V., Lebreton, M., & Dixon, L. (2025). To mask or to mirror: Human-AI alignment in collective reasoning. In Proceedings of EMNLP 2025 . arXiv:2510.01924. [37] Shi, W., Gao, M., Xu, Z., Feng, S., Xu, W., Shi, P., Zettlemoyer, L., & Tsvetkov, Y. (2024). LongMemEval: Benchmarking chat assistants on lo","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"gains under the same runtime budget, supporting the principle that memory should preserve the distinctions that matter for decisions, not descriptions. 1 Introduction Large language model (LLM) agents increasingly operate over long interaction horizons. They must answer using earlier dialogue, plan from past observations, and adapt behavior using feedback accumulated across trials and sessions [43, 34]. Yet long-horizon interaction remains bottlenecked by memory. Increasing the context window al","claim_type":"dataset","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"These results suggest that structured intent routing and deterministic evidence preparation can make limited-capacity models substantially more effective in resource-constrained long-horizon agents. 1 Introduction Language agents operating over long-horizon interactions must answer queries whose evidence spans many turns, sessions, and topic shifts [43, 25, 30, 32]. The common strategy of appending the full history causes unbounded memory growth, high cost, and degraded reasoning once inputs exc","claim_type":"dataset","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"FILCO [176]; Provence [23]; DSLR [65]; Adaptive-RAG [69] LLMLingua [70]; LongLLMLingua [71]; LLMLingua-2 [130]; RECOMP [189]; Compression for RAG [91]; Gist Tokens [119]; ICAE [45]; xRAG [22]; Token-efficiency objective [190] Lost in the Middle [100]; Topology-aware ordering [136]; OP-RAG [197]; Irrelevant-context robust- ness [151] Conflict-aware assembly [170, 187]; Chain-of-Note [199]; Astute RAG [169]; Conflict diagnostics [15, 98]; OpenDecoder [118] Fine-grained Attribution Safety Evaluatio","claim_type":"method","confidence":0.85,"evidence_strength":"citation_context"},{"claim_text":"such as Healthcare Agent [26], LD-Agent [18], and AMDS [36] demonstrate the promise of LLMs in healthcare, but they generally treat memory as a static component rather than a long-horizon, continuously updated system. Agent Memory Benchmarks.Existing benchmarks are largely eitherdialogue-centricorlong-context. Dialogue- centric benchmarks, such as LoCoMo [ 21], LongMemEval [ 34], MemoryAgentBench [ 14], HaluMem [ 4], and AMA-Bench [42], evaluate conversational memory, memory operations, or agent","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (6 contexts).","role_counts":[{"n":6,"context_role":"background"},{"n":3,"context_role":"dataset"},{"n":2,"context_role":"baseline"},{"n":2,"context_role":"method"}]},"error":null,"updated_at":"2026-07-03T10:54:03.473936+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","claims":[{"claim_text":"Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assista","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:19:50.422648+00:00"}},"summary":{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","claims":[{"claim_text":"Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assista","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":21},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":16},{"title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","work_id":"2d8c9fb7-9ace-4925-8fe1-f4e44625d04c","shared_citers":15},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":15},{"title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","work_id":"515c933e-12ae-439d-a7ff-c07fee482dfb","shared_citers":12},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":10},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":9},{"title":"Memory in the Age of AI Agents","work_id":"1ff75a14-302e-4906-aa86-1f96fbcf12ff","shared_citers":8},{"title":"Evaluating memory in llm agents via incremental multi-turn interactions","work_id":"df5096c3-e738-472b-953c-fb510ee9e68d","shared_citers":7},{"title":"Ama-bench: Evaluating long-horizon memory for agentic applications","work_id":"511e9b37-73a4-4ced-9b91-1bc2798c3c5c","shared_citers":6},{"title":"arXiv:2405.14831 [cs.CL] https://arxiv.org/abs/2405.14831","work_id":"c964b1e8-cbf5-49dd-ac34-b8f733b02a9d","shared_citers":5},{"title":"Evaluating very long-term conversational memory of LLM agents","work_id":"6bbf9aa9-b06f-489e-8977-aeb1261f2ef8","shared_citers":5},{"title":"Memorybank: Enhancing large language models with long-term memory","work_id":"3f0e5fbe-8eb1-48c4-9e30-cf41428c3046","shared_citers":5},{"title":"Memos: A memory os for ai system","work_id":"e686f058-6c5c-4484-a88e-26d945657ed3","shared_citers":5},{"title":"Mirix: Multi-agent memory system for llm-based agents","work_id":"bcb99885-6f76-4bd6-b442-e5f455bb6447","shared_citers":5},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":5},{"title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","work_id":"7058ffd2-a339-4102-89eb-248eeb074652","shared_citers":5},{"title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","work_id":"4519e90e-26c9-43ef-a89b-c8e8a8378280","shared_citers":4},{"title":"Bernstein","work_id":"b5bf85fe-4fb7-4966-b0b2-9ccf9d3b11b9","shared_citers":4},{"title":"From human memory to ai memory: A survey on memory mechanisms in the era of llms.arXiv preprint arXiv:2504.15965","work_id":"56f08885-28c9-4956-88e1-91190c6ca650","shared_citers":4},{"title":"MEM1: learning to synergize memory and reasoning for efficient long-horizon agents.CoRR, abs/2506.15841","work_id":"43cfa793-fb98-4501-8224-4dfb9e56285c","shared_citers":4},{"title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","work_id":"2a070440-2167-4398-be97-c2d4c3ee3541","shared_citers":4},{"title":"Memos: An operating system for memory-augmented generation (mag) in large language models","work_id":"62f802d2-2c22-4140-9b3d-b8b7220f772e","shared_citers":4},{"title":"my old area","work_id":"43456f70-b374-4adb-97b5-6ec329c73793","shared_citers":4}],"time_series":[{"n":32,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"86061020-1af4-475c-b28f-4eea64bf86ba","orcid":null,"display_name":"Di Wu","source":"manual","import_confidence":0.72},{"id":"0e65188c-1a9d-4ee4-b5e2-248f93ab1083","orcid":null,"display_name":"Dong Yu","source":"manual","import_confidence":0.72},{"id":"06e04a2b-a439-46c8-ad92-ec459ac7b693","orcid":null,"display_name":"Hongwei Wang","source":"manual","import_confidence":0.72},{"id":"83d1a88e-067b-4af3-a79e-df5e6a06a84e","orcid":null,"display_name":"Kai-Wei Chang","source":"manual","import_confidence":0.72},{"id":"4249b1a9-b59a-4bb1-bd2a-eb7e0cfebb9b","orcid":null,"display_name":"Wenhao Yu","source":"manual","import_confidence":0.72},{"id":"f97ef65b-7941-4af2-ab5f-2eb38cdabe9c","orcid":null,"display_name":"Yuwei Zhang","source":"manual","import_confidence":0.72}]}}