Paper Citation Record · LEDGER

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

As of 10 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 2 inbound Pith citation observations for arXiv:2607.06595.

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

pith.paper-citation-record.v1
2607.06595 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T05:27:35.040138Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T01:33:20.388698Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact0
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 439a6131-64de-4141-b4d9-639aa158f240 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Toolformer: Language models can teach themselves to use tools,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd4435d-1d6e-4456-a70e-8796c658c16b · outbound

This paper cites A survey on large language model based autonomous agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents A survey on large language model based autonomous agents,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c9643f8-c00f-4071-ab8d-f96b6b8aab9b · outbound

This paper cites MemGPT: towards LLMs as operating systems.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents MemGPT: towards LLMs as operating systems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d40773f-6347-4e64-9643-a1e7c4392c90 · outbound

This paper cites Expel: Llm agents are experiential learners,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Expel: Llm agents are experiential learners,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54753d03-72d8-433e-96ae-8de03fb148ed · outbound

This paper cites Memory os of ai agent,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Memory os of ai agent,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfdead94-6d49-467f-bceb-06386909c844 · outbound

This paper cites RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a2c860a-ca9c-4d5e-8088-23af18c96d8a · outbound

This paper cites GPT-4 Technical Report.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents GPT-4 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76170cff-b2eb-43e3-84c7-1c869a4001a8 · outbound

This paper cites Introducing Devin, the first AI software engineer,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Introducing Devin, the first AI software engineer,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 101269e8-895f-4a7c-849f-569e5e2a9ebf · outbound

This paper cites Adaptive Memory Admission Control for LLM Agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Adaptive Memory Admission Control for LLM Agents,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83025ee0-ec0b-4f3f-bf5d-b679f31f57b4 · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b0f7603-85bd-4f60-a3a7-6c2c030d00b3 · outbound

This paper cites Memory Injection Attacks on LLM Agents via Query-Only Interac- tion,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Memory Injection Attacks on LLM Agents via Query-Only Interac- tion,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913b7b37-c809-4fa1-a761-0f213309815b · outbound

This paper cites Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Agentdojo: A dynamic environment to evaluate prompt injection attacks and defenses for llm agents,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47ab995c-1bd6-438c-add8-02c77ad0258a · outbound

This paper cites OpenAgents: An Open Platform for Language Agents in the Wild.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents OpenAgents: An Open Platform for Language Agents in the Wild

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1896d1b-b113-4be5-9465-f5ec3913cd39 · outbound

This paper cites AutoGPT,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents AutoGPT,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e56749a4-3202-46bd-9d87-cf2244a1b841 · outbound

This paper cites BabyAGI,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents BabyAGI,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd31218-394a-4bc7-8e16-876c6aaaa0ef · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents React: Synergizing reasoning and acting in language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a528ffe-fb07-409f-aaaa-cb39a9c338ef · outbound

This paper cites Claude Model Card,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Claude Model Card,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2070d7f4-5965-4433-94be-3f515fb4f666 · outbound

This paper cites The rise and potential of large language model based agents: A survey,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents The rise and potential of large language model based agents: A survey,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cb5f664-c60f-4a0c-80e5-2f0ffac54e2a · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Retrieval- augmented generation for knowledge-intensive nlp tasks,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b952ba-b905-48b4-a442-7fc239be80e9 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1655aba4-52c6-4dd0-ae2b-a7d6fd42b200 · outbound

This paper cites Generative agents: Interactive simulacra of human behavior,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Generative agents: Interactive simulacra of human behavior,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8616f16c-5268-483f-bfe5-fb4d7d9cb2bd · outbound

This paper cites A-MEM: Agentic Memory for LLM Agents.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents A-MEM: Agentic Memory for LLM Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b17f0a-69a3-478b-9893-15562eb0ebc7 · outbound

This paper cites Reflexion: Language Agents with Verbal Reinforcement Learning.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Reflexion: Language Agents with Verbal Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08d81bb-167f-4fb2-8e64-fd11d9305024 · outbound

This paper cites Hackers hijacked instagram accounts by tricking meta ai support chatbot into granting access,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Hackers hijacked instagram accounts by tricking meta ai support chatbot into granting access,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4228350-0c31-44fb-8937-5ed4050a6f1b · outbound

This paper cites Zombie agents: Persistent control of self-evolving llm agents via self-reinforcing injections,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Zombie agents: Persistent control of self-evolving llm agents via self-reinforcing injections,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 801851be-3829-4ce5-ada2-5d5e9e7cabf5 · outbound

This paper cites MemoryGraft: Persistent compromise of LLM agents via poisoned experience retrieval,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents MemoryGraft: Persistent compromise of LLM agents via poisoned experience retrieval,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e789a2f-5f24-4c3f-bf2d-50111373dfe8 · outbound

This paper cites A-memguard: A proactive defense framework for llm-based agent memory,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents A-memguard: A proactive defense framework for llm-based agent memory,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d80328a-75fa-443f-96b2-fd4e9241aae9 · outbound

This paper cites The enron corpus: A new dataset for email classification research,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents The enron corpus: A new dataset for email classification research,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d06a7a8-f0fc-4ed2-a601-49e5fc1cc35c · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d944d67-17a4-4950-90df-6f9bedeb559e · outbound

This paper cites C-Pack: Packed Resources For General Chinese Embeddings.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents C-Pack: Packed Resources For General Chinese Embeddings

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85ab5fa-1dd9-4d5f-95e7-44b0c4766197 · outbound

This paper cites Internet Crime Report 2023,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Internet Crime Report 2023,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59711235-f876-4f4d-b995-cb147ffedc2d · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45de8a54-8d34-4d72-a56c-c1e9d575db57 · outbound

This paper cites Letta: Build and deploy stateful agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Letta: Build and deploy stateful agents,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fef317c-697c-4d20-aa0e-7cd3c883e305 · outbound

This paper cites Evaluating very long-term conversational memory of llm agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Evaluating very long-term conversational memory of llm agents,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876bc714-5593-4b05-b08c-077639e91d4c · outbound

This paper cites HotpotQA: A dataset for diverse, explainable multi- hop question answering,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents HotpotQA: A dataset for diverse, explainable multi- hop question answering,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0497be8b-4cd5-4b85-ba41-dbcb221ac661 · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Webshop: Towards scalable real-world web interaction with grounded language agents,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 848fd943-adbd-4482-be73-8c25315b84c7 · outbound

This paper cites Defending against prompt injection with datafilter,.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents Defending against prompt injection with datafilter,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f52f77-7077-4c43-a311-f9e780b67435 · outbound

This paper cites PromptArmor: Simple yet Effective Prompt Injection Defenses.

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents PromptArmor: Simple yet Effective Prompt Injection Defenses

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-11T05:27:35.040138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 53377e7c-862e-442f-991b-047f60b79486 · inbound

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response cites this paper.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T02:40:29.364739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2b64cf-abef-4114-9ad0-1c5b1834b20d · inbound

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response cites this paper.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.388698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.