Paper Citation Record · LEDGER

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

As of 8 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2607.23444.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.23444 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-30T22:03:10.012682Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved39
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0ff3621f-4693-4592-95d7-959af7904f44 · outbound

This paper cites Conversational Health Agents: A Personalized LLM-Powered Agent Framework.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Conversational Health Agents: A Personalized LLM-Powered Agent Framework

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.844930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f26f39-f193-416d-9ddf-802aae1aaa2c · outbound

This paper cites Improving language models by retrieving from trillions of tokens.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Improving language models by retrieving from trillions of tokens

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.849969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b6458b-5939-4a80-aed4-ede442756330 · outbound

This paper cites A Survey on Evaluation of Large Language Models.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents A Survey on Evaluation of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.854321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e349ab8-6279-4af2-bde6-e770c740c163 · outbound

This paper cites Ms marco: Benchmarking ranking models in the large-data regime.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Ms marco: Benchmarking ranking models in the large-data regime

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.858554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f44e042-625e-4040-9c02-5f0654076a08 · outbound

This paper cites Agentdojo: A dynamic en- vironment to evaluate prompt injection attacks and defenses for llm agents.Advances in Neu- ral Information Processing Systems, 37:82895– 82920, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Agentdojo: A dynamic en- vironment to evaluate prompt injection attacks and defenses for llm agents.Advances in Neu- ral Information Processing Systems, 37:82895– 82920, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.862623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94b76fab-11f4-4057-bcb3-9a884ab8af54 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.866541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed4d977a-b3d5-43c5-9c95-8b531d6f5670 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated appli- cations with indirect prompt injection.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Not what you’ve signed up for: Compromising real-world llm-integrated appli- cations with indirect prompt injection

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.870956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cc1dcac-86b3-4ca4-8684-cf594a65a26e · outbound

This paper cites [Online].

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents [Online]

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.874582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc13bef8-f132-494f-9f70-d3217d8d8464 · outbound

This paper cites Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.878034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee004766-e59d-4baa-a4f3-adbb103f1609 · outbound

This paper cites PhD thesis, OW ASP, 2025.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents PhD thesis, OW ASP, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.882064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2895147-5c3b-4cf4-82e7-c38046f32136 · outbound

This paper cites Dense passage retrieval for open-domain question answering.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Dense passage retrieval for open-domain question answering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.886022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1429b973-643c-4e35-9e06-1ebed3513628 · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks.Advances in neural information pro- cessing systems, 33:9459–9474, 2020.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Retrieval- augmented generation for knowledge-intensive nlp tasks.Advances in neural information pro- cessing systems, 33:9459–9474, 2020

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.889779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc7ce4b-ce16-45de-a9a9-a7a80feab129 · outbound

This paper cites Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.897534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e9534df-06d6-4b4f-8b6b-d315db66ea6d · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.901388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11fb0b98-4adc-4d5b-9d54-29345a511628 · outbound

This paper cites Evaluating Very Long-Term Conversational Memory of LLM Agents.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Evaluating Very Long-Term Conversational Memory of LLM Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.905552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bacc32e-4be8-49e2-9f96-795d00d37c59 · outbound

This paper cites Gpt-5-mini, 2023.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Gpt-5-mini, 2023

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.909406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5672d02a-aaa7-4fc2-80dd-2c190a5de9dc · outbound

This paper cites Generative agents: Interac- tive simulacra of human behavior.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Generative agents: Interac- tive simulacra of human behavior

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.913185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02a82bf0-7492-42d2-9778-f3656c5918f9 · outbound

This paper cites Gorilla: Large lan- guage model connected with massive apis.Ad- vances in Neural Information Processing Sys- tems, 37:126544–126565, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Gorilla: Large lan- guage model connected with massive apis.Ad- vances in Neural Information Processing Sys- tems, 37:126544–126565, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.917391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481294e0-57d9-480b-b4b1-ffdf9cc66245 · outbound

This paper cites Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.921668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0693efa8-4e72-4866-bd65-9d9ae73a1cf3 · outbound

This paper cites Tool learning with foundation models.ACM Computing Surveys, 57(4):1–40, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Tool learning with foundation models.ACM Computing Surveys, 57(4):1–40, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.925923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe5b2fb-4b3d-42bd-8a84-e262bedb42f2 · outbound

This paper cites In-context retrieval- augmented language models.Transactions of the Association for Computational Linguistics, 11:1316–1331, 2023.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents In-context retrieval- augmented language models.Transactions of the Association for Computational Linguistics, 11:1316–1331, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.929839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b4ff696-9d03-4866-84f3-a1d7f2154990 · outbound

This paper cites Replug: Retrieval-augmented black-box language mod- els.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Replug: Retrieval-augmented black-box language mod- els

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.933657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56cee30-502c-4158-ad75-e1ae8d007922 · outbound

This paper cites EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.937895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf60e53c-830d-438f-a7d9-148aba43307b · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Gemini: A Family of Highly Capable Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.941840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9163724-0ec2-4dac-96ac-dcc115debf2b · outbound

This paper cites BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.945696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb3a6cf-1e08-4d7b-b7ba-7279453c5d97 · outbound

This paper cites Adapted large language models can out- perform medical experts in clinical text sum- marization.Nature medicine, 30(4):1134–1142, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Adapted large language models can out- perform medical experts in clinical text sum- marization.Nature medicine, 30(4):1134–1142, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.949819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92db0fcc-ef49-4083-9498-e462bad3b751 · outbound

This paper cites SCM: Enhancing Large Language Model with Self-Controlled Memory Framework.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents SCM: Enhancing Large Language Model with Self-Controlled Memory Framework

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.953585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4742da1c-f88c-4a14-b353-4787356bb2bc · outbound

This paper cites Unveiling Privacy Risks in LLM Agent Memory.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Unveiling Privacy Risks in LLM Agent Memory

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.957580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f7d121d-c90b-443c-8792-cbc90581be44 · outbound

This paper cites A survey on large language model based au- tonomous agents.Frontiers of Computer Sci- ence, 18(6), March 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents A survey on large language model based au- tonomous agents.Frontiers of Computer Sci- ence, 18(6), March 2024

Reference 30

Resolution: malformed identifier; no resolver link, observed 2026-07-30T22:03:09.961668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e78d54f-83b6-4436-99ae-1acd18d6c2a3 · outbound

This paper cites Text Embeddings by Weakly-Supervised Contrastive Pre-training.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Text Embeddings by Weakly-Supervised Contrastive Pre-training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.965925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0237fab-34df-47ca-ba6b-67e7e91c09bd · outbound

This paper cites Silent leaks: Implicit knowledge extraction attack on rag systems through benign queries, 2025.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Silent leaks: Implicit knowledge extraction attack on rag systems through benign queries, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.970140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a322e7d9-fe88-4e01-82f8-537afe86dc8a · outbound

This paper cites TradingAgents: Multi-Agents LLM Financial Trading Framework.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents TradingAgents: Multi-Agents LLM Financial Trading Framework

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.974104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecd4c609-5552-4ea7-8bf6-f6c6bb377b88 · outbound

This paper cites Watch out for your agents! investigating backdoor threats to llm- based agents.Advances in Neural Information Processing Systems, 37:100938–100964, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Watch out for your agents! investigating backdoor threats to llm- based agents.Advances in Neural Information Processing Systems, 37:100938–100964, 2024

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.978827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4824f2e5-cea4-49c5-8991-0ba6fb6bee64 · outbound

This paper cites In33rd USENIX Security Symposium (USENIX Secu- rity 24), pages 4657–4674, 2024.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents In33rd USENIX Security Symposium (USENIX Secu- rity 24), pages 4657–4674, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.983079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c57c638d-bcde-4ed5-9cb2-d1d2d9447209 · outbound

This paper cites FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.986954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd0c19f6-e574-447c-b03d-a71434ea876c · outbound

This paper cites The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG).

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.991328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 245c14bd-6156-45b4-9fb3-078ac453d8bd · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.995584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6746fd5-bf8a-4176-824b-62195a6b2901 · outbound

This paper cites Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:09.999959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28abf9e-bfe4-43c0-b0d8-0880c9ccd3ad · outbound

This paper cites Memengine: A unified and modular library for developing ad- vanced memory of llm-based agents.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Memengine: A unified and modular library for developing ad- vanced memory of llm-based agents

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:10.003899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4e6206-168c-477d-8dfc-f749f44647f9 · outbound

This paper cites A Survey of Large Language Models.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents A Survey of Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-30T22:03:10.007669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a14c275-8b1f-4d63-8c94-1ca6153ac1b4 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 42

Resolution: malformed identifier; no resolver link, observed 2026-07-30T22:03:10.012682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.