{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CFXQONPJ7AQKHU6RWPFG7ONFM7","short_pith_number":"pith:CFXQONPJ","schema_version":"1.0","canonical_sha256":"116f0735e9f820a3d3d1b3ca6fb9a567d78f4c82f6c3922890fed2dfb5c5b491","source":{"kind":"arxiv","id":"2311.08719","version":1},"attestation_state":"computed","paper":{"title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"BinBin Hu, Guannan Zhang, Jinjie Gu, Lei Liu, Xiaoyan Yang, Yue Shen, Zhiqiang Zhang","submitted_at":"2023-11-15T06:08:35Z","abstract_excerpt":"Memory-augmented Large Language Models (LLMs) have demonstrated remarkable performance in long-term human-machine interactions, which basically relies on iterative recalling and reasoning of history to generate high-quality responses. However, such repeated recall-reason steps easily produce biased thoughts, \\textit{i.e.}, inconsistent reasoning results when recalling the same history for different questions. On the contrary, humans can keep thoughts in the memory and recall them without repeated reasoning. Motivated by this human capability, we propose a novel memory mechanism called TiM (Thi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.08719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T06:08:35Z","cross_cats_sorted":[],"title_canon_sha256":"c323d245e0aaebf59c429700d4e0ed1b43dbb6c69cfe40d1c2a291975e973de3","abstract_canon_sha256":"faa843dc001502cf848d58a1e22b3abb04482ad9c3a331a09cdb37e3b66c0479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:02.345481Z","signature_b64":"rOVwXdXXSiT6QDCkNZJLgFNMQJWJlAb2i0zU0B2VtUj3v71PyhnebC6W6oV983ihdHzGgh5jcq7RKuDFyziQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116f0735e9f820a3d3d1b3ca6fb9a567d78f4c82f6c3922890fed2dfb5c5b491","last_reissued_at":"2026-07-05T07:13:02.344967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:02.344967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"BinBin Hu, Guannan Zhang, Jinjie Gu, Lei Liu, Xiaoyan Yang, Yue Shen, Zhiqiang Zhang","submitted_at":"2023-11-15T06:08:35Z","abstract_excerpt":"Memory-augmented Large Language Models (LLMs) have demonstrated remarkable performance in long-term human-machine interactions, which basically relies on iterative recalling and reasoning of history to generate high-quality responses. However, such repeated recall-reason steps easily produce biased thoughts, \\textit{i.e.}, inconsistent reasoning results when recalling the same history for different questions. On the contrary, humans can keep thoughts in the memory and recall them without repeated reasoning. Motivated by this human capability, we propose a novel memory mechanism called TiM (Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08719","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.08719/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.08719","created_at":"2026-07-05T07:13:02.345032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08719v1","created_at":"2026-07-05T07:13:02.345032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08719","created_at":"2026-07-05T07:13:02.345032+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFXQONPJ7AQK","created_at":"2026-07-05T07:13:02.345032+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFXQONPJ7AQKHU6R","created_at":"2026-07-05T07:13:02.345032+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFXQONPJ","created_at":"2026-07-05T07:13:02.345032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19847","citing_title":"AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06055","citing_title":"When Should Memory Stay Silent: Measuring Memory-Use Boundaries in Memory-Augmented Conversational Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15102","citing_title":"Improving Multi-turn Dialogue Consistency with Self-Recall Thinking","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30260","citing_title":"How LoRA Remembers? A Parametric Memory Law for LLM Finetuning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19847","citing_title":"AtomMem: Building Simple and Effective Memory System for LLM Agents via Atomic Facts","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05704","citing_title":"SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":261,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18854","citing_title":"Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01970","citing_title":"Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2504.15965","citing_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19756","citing_title":"WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02522","citing_title":"Opal: Private Memory for Personal AI","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2402.02716","citing_title":"Understanding the planning of LLM agents: A survey","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09942","citing_title":"HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05704","citing_title":"SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01970","citing_title":"Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06845","citing_title":"HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7","json":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7.json","graph_json":"https://pith.science/api/pith-number/CFXQONPJ7AQKHU6RWPFG7ONFM7/graph.json","events_json":"https://pith.science/api/pith-number/CFXQONPJ7AQKHU6RWPFG7ONFM7/events.json","paper":"https://pith.science/paper/CFXQONPJ"},"agent_actions":{"view_html":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7","download_json":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7.json","view_paper":"https://pith.science/paper/CFXQONPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08719&json=true","fetch_graph":"https://pith.science/api/pith-number/CFXQONPJ7AQKHU6RWPFG7ONFM7/graph.json","fetch_events":"https://pith.science/api/pith-number/CFXQONPJ7AQKHU6RWPFG7ONFM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7/action/storage_attestation","attest_author":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7/action/author_attestation","sign_citation":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7/action/citation_signature","submit_replication":"https://pith.science/pith/CFXQONPJ7AQKHU6RWPFG7ONFM7/action/replication_record"}},"created_at":"2026-07-05T07:13:02.345032+00:00","updated_at":"2026-07-05T07:13:02.345032+00:00"}