Paper Citation Record · LEDGER

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

As of 11 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2604.09747.

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

pith.paper-citation-record.v1
2604.09747 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:57:59.918483Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T08:11:30.091859Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T10:59:47.026842Z

Reference resolution

28 of 28 outbound references displayed

verified exact20
verified fuzzy4
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 751e182f-d888-4e85-bff5-6d7c21639e53 · outbound

This paper cites Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.624741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d5e918a-e414-4215-9174-df52865e9e4f · outbound

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

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:45:57.708451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2203f6b0-c840-45fa-89a4-579d7ffa43c6 · outbound

This paper cites Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:45:57.680222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f87a458-9827-4d2a-9c74-dfa02ad46705 · outbound

This paper cites Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.658270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf83c934-f01d-4c09-9ee9-cdd86038b2d4 · outbound

This paper cites Large language model agent in financial trading: A survey.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Large language model agent in financial trading: A survey

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.633726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 03cebfc9-60e4-44e2-a376-3305b85e58d8 · outbound

This paper cites Adversarial Active Learning for Deep Networks: a Margin Based Approach.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Adversarial Active Learning for Deep Networks: a Margin Based Approach

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.651278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e00b0dbd-f8ea-47ca-a3d7-f91c84d2ba3d · outbound

This paper cites A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T23:21:42.844044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 083ffe2e-8187-4e5c-a6ca-c01bc7b14ee7 · outbound

This paper cites LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.700046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 07255138-ef1b-49e4-8486-4a513533991d · outbound

This paper cites Mistral 7B.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Mistral 7B

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T05:45:57.628644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T22:08:12.954417+00:00.

Observation 67eb77b1-719c-4bfc-958c-616813410f69 · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Certifying LLM Safety against Adversarial Prompting

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.667592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9530e74a-7c18-45c6-abf6-8bb4359c6420 · outbound

This paper cites LegalAgentBench: Evaluating LLM Agents in Legal Domain.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying LegalAgentBench: Evaluating LLM Agents in Legal Domain

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.687924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5cea52e8-2fd2-485a-aa0f-0811885a6a29 · outbound

This paper cites Self-evolving Agents with reflective and memory-augmented abilities.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Self-evolving Agents with reflective and memory-augmented abilities

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.602912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6ccfe973-97ea-404d-a1d6-460e3f42b1b4 · outbound

This paper cites EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.598580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0be60906-ab53-42b9-bd10-63ff203f1f45 · outbound

This paper cites Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.547512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b84a2e89-6678-4506-95b3-532284784310 · outbound

This paper cites Query rewriting in retrieval-augmented large language models.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Query rewriting in retrieval-augmented large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T07:54:17.443216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f257f52f-229d-4dd3-8934-789691e0a5d3 · outbound

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

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Evaluating Very Long-Term Conversational Memory of LLM Agents

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:05:17.171076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 96f781f4-4838-4c62-be3a-574b561abaf0 · outbound

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

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.588526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a4c07cd-c7a5-471b-82df-f2ddcebe2b32 · outbound

This paper cites Summary the savior: Harmful keyword and query-based summarization for llm jailbreak defense.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Summary the savior: Harmful keyword and query-based summarization for llm jailbreak defense

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T07:54:17.446396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 40b97204-2b24-4aea-97f1-f874347ca58d · outbound

This paper cites Active Learning for Convolutional Neural Networks: A Core-Set Approach.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Active Learning for Convolutional Neural Networks: A Core-Set Approach

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.524791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e9650b3-d7be-45b0-9778-765f6bfc539f · outbound

This paper cites Ehragent: Code empowers large language models for few-shot complex tabular reasoning on electronic health records.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Ehragent: Code empowers large language models for few-shot complex tabular reasoning on electronic health records

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T07:54:17.449810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 444065d5-576e-4e03-9dfb-5f45a9e04ae4 · outbound

This paper cites Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-13T03:26:34.894571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1e5aa238-e326-4c91-99fe-f3adb85290d6 · outbound

This paper cites Unveiling Privacy Risks in LLM Agent Memory.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Unveiling Privacy Risks in LLM Agent Memory

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.573091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8a6ee22-da7a-4884-9f88-a3c118714fda · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.609447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 425147d5-6c25-488c-a42e-66ccb8b624ef · outbound

This paper cites Rag-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model.arXiv preprint arXiv:2402.10828.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Rag-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model.arXiv preprint arXiv:2402.10828

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.583252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3427a164-03d4-4836-b9fa-6d04b5f0bdfd · outbound

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

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:45:57.537877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 047feef7-0a81-48ba-8f78-7d7c9c92257e · outbound

This paper cites random-word initialization.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying random-word initialization

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T07:54:17.452856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7a129496-8f79-40c1-90cc-eb568f0f4e28 · outbound

This paper cites In our experiments, we use both prefix injections (task-oriented prompts) and suffix injections (aligned with the agent’s task), as summarized in Table.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying In our experiments, we use both prefix injections (task-oriented prompts) and suffix injections (aligned with the agent’s task), as summarized in Table

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T07:54:17.440245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0b19e5f4-7dac-48e3-8340-c3bc29054601 · outbound

This paper cites an unresolved cited work.

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-17T07:54:17.455494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation c5d4d95f-317a-4522-ad81-b235bf09bfea · inbound

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies cites this paper.

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-04T10:59:47.028391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.