Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-20T10:51:19.555985Z
Paper Citation Record · LEDGER
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
As of 4 August 2026, this Paper Citation Record lists 100 of 109 outbound references and 4 inbound Pith citation observations for arXiv:2605.17830.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-30T11:45:09.621252Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-02T12:36:56.759987Z
Reference resolution
100 of 109 outbound references displayed
- verified exact19
- verified fuzzy47
- unresolved5
- parse uncertain3
- malformed identifier0
- metadata mismatch26
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 3a8a59e0-d98d-4f1a-8f7b-334c20e2742c · outbound
This paper cites Scaling Learning Algorithms Towards.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Scaling Learning Algorithms Towards
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.820004Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c7efa8f2-ef76-4144-84a9-ff4295de0a11 · outbound
This paper cites and Osindero, Simon and Teh, Yee Whye , journal =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents and Osindero, Simon and Teh, Yee Whye , journal =
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.821792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 79b85c49-cbd6-43f6-ae71-a7986f91e0e7 · outbound
This paper cites 2016 , publisher=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents 2016 , publisher=
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.809290Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5b0d3cbb-4b09-4352-b8a8-eb0c035f49ba · outbound
This paper cites author=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents author=
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.804701Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c244e857-9886-4836-88d0-3c4ced0d6b23 · outbound
This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.422906Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5dc6b148-743b-4988-bcf8-19322657a440 · outbound
This paper cites ACM Transactions on Information Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents ACM Transactions on Information Systems , volume=
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.799480Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6fcd6728-5883-4a3e-a1a3-7a0734f3bced · outbound
This paper cites From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.429043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 02bac776-c712-44dd-a890-168dd5df231d · outbound
This paper cites In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.419747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 17e4f1ab-10fa-4ee9-a6c9-232e05a900d5 · outbound
This paper cites Unveiling Privacy Risks in LLM Agent Memory.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unveiling Privacy Risks in LLM Agent Memory
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.426144Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1f316f85-0ec2-4eca-a292-66c7583bb89f · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.793801Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a23c9e2a-e01f-40be-8c6f-8897ea70810a · outbound
This paper cites 2024 , publisher=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents 2024 , publisher=
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.807074Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bf06375c-161f-4a20-8579-e26a14fc7f85 · outbound
This paper cites Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents
Reference 13
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.280521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e24abe70-9fe7-440e-9c02-52369405f433 · outbound
This paper cites 34th USENIX Security Symposium (USENIX Security 25) , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents 34th USENIX Security Symposium (USENIX Security 25) , pages=
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.096169Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b20449c7-f3c6-4e97-b59c-ffd8f976e50c · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.098256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f4652c9c-aa2c-4e8c-b2a2-7543ca188e14 · outbound
This paper cites Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.410342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a8f796f9-ea66-4e15-9303-92903aa201d3 · outbound
This paper cites The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise
Reference 17
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.416419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3cd55bc9-462f-4c0f-a024-a0a7db99f931 · outbound
This paper cites Companion Proceedings of the ACM on Web Conference 2025 , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Companion Proceedings of the ACM on Web Conference 2025 , pages=
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.089927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7eebb96a-b969-4fee-af66-52cfcb4608aa · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.087990Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1a4ab1ae-b1fa-4938-932c-da8b38306c92 · outbound
This paper cites Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.295767Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f8446c93-5547-459d-82a8-573bbff0dc4c · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.092153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1df25b65-ad67-45e4-90df-7cf232614560 · outbound
This paper cites CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.407325Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9d158abf-15b0-4a0b-a834-038b986e3cbd · outbound
This paper cites Agentdam: Privacy leakage evaluation for autonomous web agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Agentdam: Privacy leakage evaluation for autonomous web agents
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.362236Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 97c55fa5-8be5-47a3-84d6-6f63219e8a96 · outbound
This paper cites Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.365092Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fd550343-58cc-42b5-b7e3-2c4e33499593 · outbound
This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.820669Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b44b6da1-bc45-46fa-b03e-879abad00c77 · outbound
This paper cites European conference on machine learning , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents European conference on machine learning , pages=
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.811407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 69c97b4e-13d7-4f7e-a6fc-2838e9f710b9 · outbound
This paper cites A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.292678Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 91a16e95-bf7b-49de-96b2-461640bd205a · outbound
This paper cites Shicheng Fang, Yuxin Wang, Xiaoran Liu, Jiahao Lu, Chuanyuan Tan, Xinchi Chen, Yining Zheng, Xuanjing Huang, and Xipeng Qiu.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Shicheng Fang, Yuxin Wang, Xiaoran Liu, Jiahao Lu, Chuanyuan Tan, Xinchi Chen, Yining Zheng, Xuanjing Huang, and Xipeng Qiu
Reference 28
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.274416Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation da358440-c146-4827-a0a6-6ff9037c1522 · outbound
This paper cites Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
Reference 29
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.385754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation aaf9818a-e34a-42b1-b8db-00ca347dbb49 · outbound
This paper cites Proceedings of the 36th annual acm symposium on user interface software and technology , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the 36th annual acm symposium on user interface software and technology , pages=
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.817743Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ba05d066-49fe-4e9e-b873-3ec9131552dd · outbound
This paper cites International Conference on Database Systems for Advanced Applications , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents International Conference on Database Systems for Advanced Applications , pages=
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.823868Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4735e4ef-ea54-4567-954c-328f1ec8eca5 · outbound
This paper cites From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
Reference 32
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.401138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 375d7b61-9f63-4ad3-bb4d-04d4f8d7198e · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.815882Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f0edfc22-7689-4f5a-bd33-6cf57712a0a2 · outbound
This paper cites Operationalizing Contextual Integrity in Privacy-Conscious Assistants.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Operationalizing Contextual Integrity in Privacy-Conscious Assistants
Reference 34
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.329028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 238d00b7-bf56-41f7-b94e-aac9057940bb · outbound
This paper cites Privacybench: A conversational benchmark for evaluating privacy in personalized ai.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Privacybench: A conversational benchmark for evaluating privacy in personalized ai
Reference 35
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.277427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bbc656ef-c995-4324-a5bf-6572fbe542dd · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.812201Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 65302c32-d336-459d-a7cf-6b7e0f8992ae · outbound
This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Findings of the Association for Computational Linguistics: ACL 2025 , pages=
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.818893Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2b704929-aec8-43ec-b1dd-48179b31517f · outbound
This paper cites Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining , pages=
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.151386Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3466a402-a3fc-47f3-9ba9-9ef89a6a3799 · outbound
This paper cites arXiv preprint arXiv:2510.02373 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2510.02373 , year=
Reference 39
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.283521Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation dad512d6-2b00-49ee-8fd5-4afc814beea3 · outbound
This paper cites Large Language Model Safety: A Holistic Survey.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Large Language Model Safety: A Holistic Survey
Reference 40
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.391805Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d34fa44-71f4-4388-bb0e-e441fbe14c5d · outbound
This paper cites Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:25.817051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e1dfb9a1-ae37-4ed2-81df-4e4ba678340d · outbound
This paper cites MemOS: A Memory OS for AI System.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents MemOS: A Memory OS for AI System
Reference 42
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.337711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 96cad227-7741-49d8-8431-a1ee53d64ffd · outbound
This paper cites Memory in the Age of AI Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Memory in the Age of AI Agents
Reference 43
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.394642Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 910c82b2-c51d-4533-b49a-19b8440a114d · outbound
This paper cites arXiv preprint arXiv:2512.23343 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2512.23343 , year=
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.286331Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ea09e336-dd40-4cf3-9430-ac24057b3a55 · outbound
This paper cites ACM Computing Surveys , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents ACM Computing Surveys , year=
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.149324Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e0b15785-27a4-4df9-a10d-1d336f3f1755 · outbound
This paper cites arXiv preprint arXiv:2601.04170 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2601.04170 , year=
Reference 46
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.307165Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 799bc9bb-828d-4245-b409-efcbfb8a8f90 · outbound
This paper cites International Journal of Scientific Research in Computer Science, Engineering and Information Technology , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents International Journal of Scientific Research in Computer Science, Engineering and Information Technology , volume=
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.145694Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f51933f7-9b0d-4df9-a35e-97b4982c6206 · outbound
This paper cites Continual Learning and Catastrophic Forgetting.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Continual Learning and Catastrophic Forgetting
Reference 48
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.304305Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 961fa80c-cff8-447e-a023-ebebaf2f7454 · outbound
This paper cites ACM Computing Surveys , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents ACM Computing Surveys , volume=
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.143707Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f96fbcba-49be-46e0-a84e-08d4cb6050a5 · outbound
This paper cites arXiv preprint arXiv:2501.07278 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2501.07278 , year=
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.289438Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 58ef8054-24f6-45d5-afb1-c3aa694502c4 · outbound
This paper cites 2006 IEEE symposium on security and privacy (S&P'06) , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents 2006 IEEE symposium on security and privacy (S&P'06) , pages=
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.139302Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eed19333-62d0-460b-ac71-a35805031b37 · outbound
This paper cites arXiv preprint arXiv:2506.04245 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2506.04245 , year=
Reference 52
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.380153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f1fd8e6b-ba77-4b22-9b1d-ccc32ac3efcd · outbound
This paper cites State and Memory is All You Need for Robust and Reliable AI Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents State and Memory is All You Need for Robust and Reliable AI Agents
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.382933Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 87d76ffe-4cf3-45f5-9779-cea223b468ed · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.141533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d9ac2a69-ff07-48bb-88d9-ec94be74e5fd · outbound
This paper cites arXiv preprint arXiv:2509.18868 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2509.18868 , year=
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.298566Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cd9cbda1-dad7-4d54-b34c-78d8103fe320 · outbound
This paper cites In order to learn: How the sequence of topics influences learning , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents In order to learn: How the sequence of topics influences learning , pages=
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.135425Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 068223f8-f9c7-4ec4-bf0b-9283a4746c85 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in Neural Information Processing Systems , volume=
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.137368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ec529db9-83c1-40f9-9efc-b2619af5715a · outbound
This paper cites Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
Reference 58
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.301454Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5e56c274-67d5-442e-968a-de76088ba8c2 · outbound
This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.147593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 32adb8c4-63c3-46ce-805e-fd63b060e44b · outbound
This paper cites Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
Reference 60
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.404493Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 31ea34cf-04a0-4bab-be65-e095c7d17c6d · outbound
This paper cites Retrieval-Augmented Generation with Conflicting Evidence.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Retrieval-Augmented Generation with Conflicting Evidence
Reference 61
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.368049Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bad24a57-4924-40f8-8826-da45b8236cae · outbound
This paper cites arXiv preprint arXiv:2505.18882 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2505.18882 , year=
Reference 62
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.377045Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cdcd6088-c5d5-4783-bbe6-2a9cdfcc4e50 · outbound
This paper cites Advances in neural information processing systems , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Advances in neural information processing systems , volume=
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.122562Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation aa22587c-4b8f-4774-b6a3-7cc3acac2cb0 · outbound
This paper cites arXiv preprint arXiv:2509.01476 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2509.01476 , year=
Reference 64
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.359459Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 86d98a6c-d278-4a27-9c66-24b22301c105 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 65
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T10:53:14.113129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 601c4f36-eccd-4671-88e5-86ab310452d7 · outbound
This paper cites arXiv preprint arXiv:2510.03662 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2510.03662 , year=
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.397798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d837f3f9-6307-48c3-a4a7-4ca1c196884f · outbound
This paper cites ACM Computing Surveys , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents ACM Computing Surveys , volume=
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.125212Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation be637448-0a16-4584-8055-0200b7d20a90 · outbound
This paper cites Detecting Pretraining Data from Large Language Models.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Detecting Pretraining Data from Large Language Models
Reference 68
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.413402Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0bbb6e09-6dc5-4c5a-baa0-cef3eeee27bc · outbound
This paper cites Time Travel in LLMs: Tracing Data Contamination in Large Language Models.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Time Travel in LLMs: Tracing Data Contamination in Large Language Models
Reference 69
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.353220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 10e779bd-f1be-421f-bd88-e28d229be812 · outbound
This paper cites arXiv preprint arXiv:2502.01534 , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2502.01534 , year=
Reference 70
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.350232Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4b336feb-d7a0-4b04-a80c-ad0e46f6ee20 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 71
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T10:53:14.102052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0738d6bb-c82d-4dca-b4b3-f15ec3e730d7 · outbound
This paper cites arXiv preprint arXiv:2602.14364 , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2602.14364 , year =
Reference 72
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.316969Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 44a8b43e-cf88-41f2-99c7-a389d831552b · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 73
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T10:53:14.094191Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a727fced-2044-4fce-a630-1ec2b63e663e · outbound
This paper cites arXiv preprint , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint , year =
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.103887Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 04198a1e-a172-466e-b924-62a35674a49d · outbound
This paper cites arXiv preprint , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint , year =
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.100104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d62c5ec-d7db-4b19-aa71-3ef39a5577b4 · outbound
This paper cites AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Reference 76
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.313629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f1c7e175-6e3b-4ea1-98bf-81160a1adba6 · outbound
This paper cites arXiv preprint arXiv:2602.03255 , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2602.03255 , year =
Reference 77
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.310451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1aa98faa-8049-40a7-a4bb-9b7ce3eb869d · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 78
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T10:53:14.107532Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a237db33-a7c0-4316-8708-13f450ac8e31 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 79
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-20T10:53:25.824343Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 43412ad2-68a6-42b3-9203-b89f3ad5a981 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 80
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-20T10:53:14.131213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4f6e2e8f-c0e5-4e63-84ba-e6344d2177f1 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 81
- Resolution
- unresolved
- raw_fallback, observed 2026-05-20T10:53:14.129043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7c7ed6bd-5a2d-45c9-a759-1f64a7bee2ae · outbound
This paper cites Tom's Hardware , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Tom's Hardware , year =
Reference 82
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.133229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1d71e124-51a9-4ede-bdb9-9968e9437b18 · outbound
This paper cites arXiv preprint arXiv:2512.04864 , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents arXiv preprint arXiv:2512.04864 , year =
Reference 83
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T10:53:13.356621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c7995422-2ce5-47ad-bdb0-581e3b9ce8de · outbound
This paper cites Transactions of the Association for Computational Linguistics , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Transactions of the Association for Computational Linguistics , volume=
Reference 84
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.117707Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 13b838b7-635a-4980-aaf1-47a867e0444b · outbound
This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Agent-SafetyBench: Evaluating the Safety of LLM Agents
Reference 85
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.346572Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4d04138b-50f5-4a68-85ce-290850430f4c · outbound
This paper cites Proceedings of ICLR , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of ICLR , year =
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.127229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0eb52d8a-ce4e-495c-9b04-69fdc8b08cad · outbound
This paper cites Findings of ACL , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Findings of ACL , year =
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.105730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 91b932ff-af16-4af5-86a4-8ea7ce6997dd · outbound
This paper cites Findings of EMNLP , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Findings of EMNLP , year =
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.080213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6411e66c-0021-4082-956f-c96528da0188 · outbound
This paper cites Maddison and Tatsunori Hashimoto , title =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Maddison and Tatsunori Hashimoto , title =
Reference 89
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.082116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c3e1ec8f-4499-4ffd-9208-c1ef13c4d380 · outbound
This paper cites Proceedings of ICLR , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of ICLR , year =
Reference 90
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.083958Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ca5c1224-6b0f-408e-bdaf-f2c7da48338d · outbound
This paper cites Saltzer and Michael D.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Saltzer and Michael D
Reference 91
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.072779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6d752943-e30c-4988-b272-e4ddc9ed8a5f · outbound
This paper cites Anderson , title =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Anderson , title =
Reference 92
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.074747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4917b71a-0baa-43a3-bd79-d4b91c13d8f2 · outbound
This paper cites Biba , title =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Biba , title =
Reference 93
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.076411Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation dd88e52b-ab0e-4ef3-8f83-8cc6cc381f3a · outbound
This paper cites Elliott Bell and Leonard J.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Elliott Bell and Leonard J
Reference 94
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.071067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fe0e5439-c82c-4931-b903-32607b528367 · outbound
This paper cites an unresolved cited work.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Unresolved cited work
Reference 95
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-20T10:53:14.078414Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5fd36c9d-70b8-49cb-9939-f2a8b8f23814 · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 96
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T10:53:13.388554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a1ba41db-9655-4e9a-b675-aee5d5471a3f · outbound
This paper cites Proceedings of COLM , year =.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Proceedings of COLM , year =
Reference 97
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.085923Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8658c913-c2f4-4a1f-b769-0ed3de8f98f6 · outbound
This paper cites ACM Transactions on Software Engineering and Methodology , year=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents ACM Transactions on Software Engineering and Methodology , year=
Reference 98
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.109444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f1e47ae8-0e53-4fa2-8cac-db8406c2f4a4 · outbound
This paper cites MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
Reference 99
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.322808Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a545270b-6d8a-4836-8ad2-c6711a879f9d · outbound
This paper cites International Journal of Open Information Technologies , volume=.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents International Journal of Open Information Technologies , volume=
Reference 100
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-20T10:53:14.111248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7af66100-ddf7-46ca-bc44-f835031ab460 · outbound
This paper cites Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents.
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents Breaking the protocol: Security anal- ysis of the model context protocol specification and prompt in- jection vulnerabilities in tool-integrated llm agents
Reference 101
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T10:53:13.325672Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
Observation 21843cdc-7a07-478b-8826-34be5cb58858 · inbound
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses cites this paper.
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T17:08:58.831798Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f15b283a-7810-4fd3-8521-d0e3657d67e4 · inbound
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models cites this paper.
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T07:23:12.975464Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 298b8c8c-a81c-4b84-91d4-7aaab073bd8f · inbound
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents cites this paper.
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T12:36:56.761447Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 234cff12-39a9-46e3-a0b7-f1f32cdd9c40 · inbound
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair cites this paper.
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T11:45:09.621252Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.