Paper Citation Record · LEDGER

Seven Security Challenges in Cross-domain Multi-agent LLM Systems

As of 17 August 2026, this Paper Citation Record lists 100 of 124 outbound references and 8 inbound Pith citation observations for arXiv:2505.23847.

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

pith.paper-citation-record.v1
2505.23847 v5

Coverage vector

measured 100 of 124 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:05:36.436653Z

measured 108 of 108 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:26:33.416300Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 124 outbound references displayed

verified exact1
verified fuzzy44
unresolved55
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation cd5d8044-0d4a-4d9f-a780-0aed17a5bd8b · outbound

This paper cites N-agent ad hoc teamwork.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems N-agent ad hoc teamwork

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.745112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82b655e1-027c-4ef5-a0de-20622e45110b · outbound

This paper cites Camel: Communicative agents for "mind" exploration of large language model society.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Camel: Communicative agents for "mind" exploration of large language model society

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.838290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a15f36d-14d3-4fee-9317-b45990b7776a · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.912946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df60225-f53e-4dee-a04c-12dc02ba7e59 · outbound

This paper cites Kaminka, Sarit Kraus, and Jeffrey S.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Kaminka, Sarit Kraus, and Jeffrey S

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:28.956692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a7dd7c-f7a9-4958-9e41-1021dec7b702 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.032367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb260161-523d-4243-834c-3328a122ee80 · outbound

This paper cites Theory of mind for multi-agent collaboration via large language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Theory of mind for multi-agent collaboration via large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.102014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 213c117d-1655-49b1-9168-800ea3aa77a3 · outbound

This paper cites Privacy preserving multi-agent reinforcement learning in supply chains, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Privacy preserving multi-agent reinforcement learning in supply chains, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.248370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5d98d0b-a61d-428c-a195-80923671a0a8 · outbound

This paper cites Reflective multi-agent collaboration based on large language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Reflective multi-agent collaboration based on large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.292281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3874868-d5fa-4aec-89ee-03d51bed5a9d · outbound

This paper cites Tenenbaum, Antonio Torralba, Shuang Li, and Igor Mordatch.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Tenenbaum, Antonio Torralba, Shuang Li, and Igor Mordatch

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.380901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d6ddf26-19ac-4f83-b067-c1e5f7968545 · outbound

This paper cites Training language models to follow instructions with human feedback.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Training language models to follow instructions with human feedback

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.447650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9afa9a95-ceb4-4451-8cff-4e3cee2d56d6 · outbound

This paper cites Torr, Lewis Hammond, and Christian Schroeder de Witt.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Torr, Lewis Hammond, and Christian Schroeder de Witt

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.520206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f0a48d-cf9d-453a-84a7-b1778bed443d · outbound

This paper cites Ramchurn, and Xiaowei Huang.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Ramchurn, and Xiaowei Huang

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.604745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f8a9219-1d97-4a94-8b64-42b3c9c70d0c · outbound

This paper cites K-level reasoning for zero-shot coordination in hanabi.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems K-level reasoning for zero-shot coordination in hanabi

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.652768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef1de8e-44f4-408a-a801-30e73f7d41b4 · outbound

This paper cites Cooperation, competition, and maliciousness: Llm-stakeholders interactive negotiation.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Cooperation, competition, and maliciousness: Llm-stakeholders interactive negotiation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.745372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d1094d7-4f55-4fa6-b9ef-c0fc2920218e · outbound

This paper cites Honesty is the best policy: defining and mitigating ai deception.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Honesty is the best policy: defining and mitigating ai deception

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.817538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f2b831-5985-4828-b54a-875f21359eb6 · outbound

This paper cites Adversarial policies: Attacking deep reinforcement learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Adversarial policies: Attacking deep reinforcement learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.902590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8cdff5f-e23d-49ea-9ecb-6a609bbab56d · outbound

This paper cites Minimum coverage sets for training robust ad hoc teamwork agents.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Minimum coverage sets for training robust ad hoc teamwork agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:29.977547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e65dce-80d9-4144-8486-c9bb2c912c08 · outbound

This paper cites Other–Play.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Other–Play

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.071896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f36c422-beb3-4792-8564-5c634e71f6c4 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.145355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340912fe-7078-45b8-a56d-de8e48935cb3 · outbound

This paper cites Agents Under Siege: Breaking pragmatic multi-agent llm systems with optimized prompt attacks, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Agents Under Siege: Breaking pragmatic multi-agent llm systems with optimized prompt attacks, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.203370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02418556-4818-46a8-9066-51bf9ec5703f · outbound

This paper cites Prompt infection: LLM-to-LLM prompt injection within multi-agent systems, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Prompt infection: LLM-to-LLM prompt injection within multi-agent systems, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.276909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ced904c-5dd2-48a7-a1dd-0e28416f37d3 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.377639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea3ddad-57b2-4414-962e-7ca4ccf1af06 · outbound

This paper cites Teams of llm agents can exploit zero-day vulnerabilities, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Teams of llm agents can exploit zero-day vulnerabilities, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.450923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f30e25-4595-427a-b745-42a0ea17ee02 · outbound

This paper cites Robust multi-agent reinforcement learning via adversarial regu- larization: theoretical foundation and stable algorithms.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Robust multi-agent reinforcement learning via adversarial regu- larization: theoretical foundation and stable algorithms

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.540076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c5ee46-adfa-48f3-a263-aa3439efc15f · outbound

This paper cites Aligning individual and collective objectives in multi-agent cooperation.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Aligning individual and collective objectives in multi-agent cooperation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.600286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f31ac4f-0f86-4518-b5c8-14c60451d694 · outbound

This paper cites Emergent reciprocity and team formation from randomized uncertain social preferences.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Emergent reciprocity and team formation from randomized uncertain social preferences

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.689776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b368abec-5cfd-45bd-9a34-d237c9fbc18b · outbound

This paper cites Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.791468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f2f745-7ae9-4652-8b86-adbaa13239b8 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.878785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9872209-0d68-41aa-81da-73443577a9b0 · outbound

This paper cites Efficient adversarial attacks on online multi-agent reinforcement learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Efficient adversarial attacks on online multi-agent reinforcement learning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:30.950332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab261bd-fe1f-4b11-bd1a-b538d793599d · outbound

This paper cites Zico Kolter, and Matt Fredrikson.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Zico Kolter, and Matt Fredrikson

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.037737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f751df3-66e4-41e1-ab0e-c7035b5b74b1 · outbound

This paper cites Prompt injection attack against llm- integrated applications, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Prompt injection attack against llm- integrated applications, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.112749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d3f1a7-bb7e-4e52-bdc6-caf186b7b981 · outbound

This paper cites BERT-ATTACK: Adversarial attack against BERT using BERT.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems BERT-ATTACK: Adversarial attack against BERT using BERT

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.222704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c571e03a-df64-43c8-80fb-3dcc8643547c · outbound

This paper cites Jailbreaking gpt-4v via self- adversarial attacks with system prompts, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Jailbreaking gpt-4v via self- adversarial attacks with system prompts, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.303513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7416a4d-eba3-4257-8ae5-756ffba3f2d3 · outbound

This paper cites GPT-4 jailbreaks itself with near-perfect success using self-explanation.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems GPT-4 jailbreaks itself with near-perfect success using self-explanation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.371649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edcb3014-d23a-4a3b-af64-48db5af545ed · outbound

This paper cites Bowman, Ethan Perez, Roger Baker Grosse, and David Duvenaud.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Bowman, Ethan Perez, Roger Baker Grosse, and David Duvenaud

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.457214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c329e5f-b8e8-48d0-94fe-e42dc2fb3edd · outbound

This paper cites Universal adver- sarial triggers for attacking and analyzing NLP.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Universal adver- sarial triggers for attacking and analyzing NLP

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.589274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e24a2e6-aa23-46b7-910f-1b8757c5396e · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Tree of attacks: Jailbreaking black-box llms automatically

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.665231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a35f0f1c-29b7-4ae3-84a8-1a8a8f3c94bd · outbound

This paper cites Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.744314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e17839b3-345f-4c8a-af30-edd9343f9fe0 · outbound

This paper cites TruthfulQA: Measuring how models mimic human falsehoods.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems TruthfulQA: Measuring how models mimic human falsehoods

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.858459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c0d13c4-29d1-4dc5-9f7e-deb0ebc73c6e · outbound

This paper cites Shadow alignment: The ease of subverting safely-aligned language models, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Shadow alignment: The ease of subverting safely-aligned language models, 2023

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:31.980380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8948c4e3-bea6-43b1-96d9-6966459af042 · outbound

This paper cites Maddison, and Tatsunori Hashimoto.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Maddison, and Tatsunori Hashimoto

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:32.067401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdcccd0-68b4-44aa-b841-535f4656534b · outbound

This paper cites Visual adversarial examples jailbreak aligned large language models.Proceedings of the AAAI Conference on Artificial Intelligence, 38(19):21527–21536, Mar.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Visual adversarial examples jailbreak aligned large language models.Proceedings of the AAAI Conference on Artificial Intelligence, 38(19):21527–21536, Mar

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:32.144382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb87bd0-c9c5-48f8-a695-7c6922e1a13d · outbound

This paper cites React: Synergizing reasoning and acting in language models.International Conference on Learning Representations (ICLR).

Seven Security Challenges in Cross-domain Multi-agent LLM Systems React: Synergizing reasoning and acting in language models.International Conference on Learning Representations (ICLR)

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:32.211777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3bf585e-55b9-485d-b9cc-7dc964e90925 · outbound

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

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Toolformer: Language models can teach themselves to use tools

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:32.331651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88f4ff58-724a-42fa-acd2-c2b9f0433cbe · outbound

This paper cites Llm agents can autonomously hack websites, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Llm agents can autonomously hack websites, 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:32.425184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e00a7e9d-b027-42f3-a481-f2b8fa441f22 · outbound

This paper cites Gpt-4 hired unwitting taskrabbit worker by pretending to be ‘vision-impaired’ human, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Gpt-4 hired unwitting taskrabbit worker by pretending to be ‘vision-impaired’ human, 2023

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:49.377622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dbe0c9c5-3b8d-4da8-a60b-4d731dcaea96 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:49.231746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b1f78769-ab10-4c5c-8f63-9bbfbe7b5f24 · outbound

This paper cites Poisoning language models during instruction tuning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Poisoning language models during instruction tuning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:49.031103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e13f8022-6229-4a3a-9faa-780e049ab9b5 · outbound

This paper cites Imperio: language-guided backdoor attacks for arbitrary model control.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Imperio: language-guided backdoor attacks for arbitrary model control

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:48.846592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 74cacfe3-5ff9-4fd6-bf09-a2fa17c748fd · outbound

This paper cites Membership inference attacks against fine-tuned large language models via self-prompt calibration.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Membership inference attacks against fine-tuned large language models via self-prompt calibration

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:48.671969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f8f2d202-a0dd-4785-ae3c-70abc7a85900 · outbound

This paper cites Quantifying memorization across neural language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Quantifying memorization across neural language models

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:48.482670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 23428347-1607-43a4-a8f9-5b8c6a686d66 · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:48.283905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b51fa7eb-10e4-4ced-8573-7e46d94d565e · outbound

This paper cites Is bert really robust? a strong baseline for natural language attack on text classification and entailment.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Is bert really robust? a strong baseline for natural language attack on text classification and entailment

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:48.121686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 583b7b98-3598-41fb-a632-4217697d86bb · outbound

This paper cites Llama Guard: LLM-based input–output safeguard for human–ai conversations, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Llama Guard: LLM-based input–output safeguard for human–ai conversations, 2023

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.950929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3453d995-0b0f-40a3-84bf-9a79c44bcf8f · outbound

This paper cites an unresolved cited work.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:05:47.836039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aaa07675-66d5-403e-972f-4a7601ac92cb · outbound

This paper cites Toxicity in chatgpt: Analyzing persona-assigned language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Toxicity in chatgpt: Analyzing persona-assigned language models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.664631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e777191-1e18-4908-8167-c27014ba0e4f · outbound

This paper cites Fight back against jailbreaking via prompt adversarial tuning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Fight back against jailbreaking via prompt adversarial tuning

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.531898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 73b85902-a625-4522-aabe-44c935ac5676 · outbound

This paper cites Robust prompt optimization for defending language models against jailbreaking attacks.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Robust prompt optimization for defending language models against jailbreaking attacks

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.404794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc6bc80d-88fe-4e97-9ce9-1558f8da7112 · outbound

This paper cites Freelb: Enhanced adversarial training for natural language understanding.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Freelb: Enhanced adversarial training for natural language understanding

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:33.606451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d1cd925-9bd2-4348-8fef-4d5b7d3e3f71 · outbound

This paper cites Mat: mixed-strategy game of adversarial training in fine-tuning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Mat: mixed-strategy game of adversarial training in fine-tuning

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.293956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f89c5a0-d730-401a-8d7b-90c1b3210300 · outbound

This paper cites Adversarial self-attention for language understanding.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Adversarial self-attention for language understanding

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.141969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1aab8434-abd4-44ee-b20f-9cd2d028629d · outbound

This paper cites RoAST: Robustifying language models via adversarial perturbation with selective training.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems RoAST: Robustifying language models via adversarial perturbation with selective training

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:47.006148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bc07d6eb-4f1a-4764-a201-ebedf6ab9127 · outbound

This paper cites Fast model editing at scale.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Fast model editing at scale

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:33.975563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc57019a-1b69-4205-8b57-3a1b4fb46caf · outbound

This paper cites Evil geniuses: Delving into the safety of llm-based agents, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Evil geniuses: Delving into the safety of llm-based agents, 2024

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.886940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b78de146-a0a6-4dbc-862b-ab98bc74b22e · outbound

This paper cites A survey on trustworthy llm agents: Threats and countermeasures, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems A survey on trustworthy llm agents: Threats and countermeasures, 2025

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.734182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 58d2a244-a430-45b0-ae49-82aa988c6bb9 · outbound

This paper cites Agentsafe: Safeguarding large language model-based multi-agent systems via hierarchical data management, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Agentsafe: Safeguarding large language model-based multi-agent systems via hierarchical data management, 2025

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.602115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7fb51940-4e11-43cb-8927-b991b8dc7246 · outbound

This paper cites Watch out for your agents! investigating backdoor threats to LLM-based agents.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Watch out for your agents! investigating backdoor threats to LLM-based agents

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.441948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3ca89800-0bf1-4fd9-a63a-2b137eef6c0d · outbound

This paper cites Backdooring instruction-tuned large language models with virtual prompt injection.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Backdooring instruction-tuned large language models with virtual prompt injection

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.309645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7731c074-91a4-4f5f-ac16-a2bdec2d8b75 · outbound

This paper cites Ignore this title and HackAPrompt: Exposing systemic vulnerabilities of LLMs through a global prompt hacking competition.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Ignore this title and HackAPrompt: Exposing systemic vulnerabilities of LLMs through a global prompt hacking competition

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.192684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 82056beb-b79e-45aa-8460-adf82730efe4 · outbound

This paper cites Assessing vulnerabilities in state-of-the-art large language models through hex injection (student abstract).

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Assessing vulnerabilities in state-of-the-art large language models through hex injection (student abstract)

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:46.053018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3958708b-67f6-4fdd-a61d-4cb96369ca94 · outbound

This paper cites A hitchhiker’s guide to jailbreaking chatgpt via prompt engineering.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems A hitchhiker’s guide to jailbreaking chatgpt via prompt engineering

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.903056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b3bfe75c-85aa-4907-81f5-394cad00daa0 · outbound

This paper cites Infecting LLM agents via generalizable adversarial attack.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Infecting LLM agents via generalizable adversarial attack

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.751439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4d55c973-ec46-439f-b677-0cfab1509288 · outbound

This paper cites Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:34.718603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7497bd97-823e-4e68-8bff-2faf266bc9de · outbound

This paper cites Assessing risks of using autonomous language models in military and diplomatic planning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Assessing risks of using autonomous language models in military and diplomatic planning

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.617312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e177162d-e68a-4e9f-a1e1-382d99dbc1e8 · outbound

This paper cites Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:34.852642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022f275d-7bff-4875-a3f2-6189ac02ea30 · outbound

This paper cites Revisiting character-level adversarial attacks for language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Revisiting character-level adversarial attacks for language models

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.486931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e3ffa798-ea10-4014-8c22-e8a69128400f · outbound

This paper cites MultiAgent collaboration attack: Investigating adversarial attacks in large language model collaborations via debate.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems MultiAgent collaboration attack: Investigating adversarial attacks in large language model collaborations via debate

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.377915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0607f821-af20-4477-81c6-7fb67d3ad0ff · outbound

This paper cites Multi-turn jailbreaking large language models via attention shifting.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Multi-turn jailbreaking large language models via attention shifting

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.187546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d381ef4f-0db8-452f-8864-1030f641eda8 · outbound

This paper cites Autosafecoder: A multi-agent framework for securing llm code generation through static analysis and fuzz testing, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Autosafecoder: A multi-agent framework for securing llm code generation through static analysis and fuzz testing, 2024

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:45.050551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87bc1f94-5f39-4ef5-b8a5-41da7bef7209 · outbound

This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents, 2024

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.914609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3f987677-653a-48c7-921f-138a60f4cfbf · outbound

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

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.722825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 31aa3c04-47e7-4c5c-ae83-21cf6f396d97 · outbound

This paper cites Removing RLHF protections in GPT-4 via fine-tuning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Removing RLHF protections in GPT-4 via fine-tuning

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.544249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9c78f597-ff25-4d1f-8fd1-e21dada96d7b · outbound

This paper cites Multi-agent security tax: Trading off security and collaboration capabilities in multi-agent systems.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Multi-agent security tax: Trading off security and collaboration capabilities in multi-agent systems

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.424904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 52246df9-5b81-4e58-835f-b66c8c848810 · outbound

This paper cites Simulate and eliminate: Revoke backdoors for generative large language models.Proceedings of the AAAI Conference on Artificial Intelligence, 39(1):397–405, Apr.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Simulate and eliminate: Revoke backdoors for generative large language models.Proceedings of the AAAI Conference on Artificial Intelligence, 39(1):397–405, Apr

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.267121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b50f2879-cb40-4131-b874-524ea00071e0 · outbound

This paper cites LLM-PIRATE: A benchmark for indirect prompt injection attacks in large language models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems LLM-PIRATE: A benchmark for indirect prompt injection attacks in large language models

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:44.094832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 233faa9d-d152-40d9-9b0f-f34e74567d36 · outbound

This paper cites Immunization against harmful fine-tuning attacks.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Immunization against harmful fine-tuning attacks

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.913661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c455217a-f5c7-4cad-8f5d-0abc9f30763a · outbound

This paper cites A dynamic llm-powered agent network for task-oriented agent collaboration, 2024.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems A dynamic llm-powered agent network for task-oriented agent collaboration, 2024

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:35.598120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84b04f7c-1f48-4060-826c-1b59476fa5d0 · outbound

This paper cites BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

Reference 88

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:05:37.882879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 32e9a39a-fada-4695-a8ee-8bf69182f070 · outbound

This paper cites Clibe: Detecting dynamic backdoors in transformer-based nlp models.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Clibe: Detecting dynamic backdoors in transformer-based nlp models

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.678206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bd502494-d4a0-48cb-a9f1-cf3f856f9ccc · outbound

This paper cites Jfrog and hugging face join forces to expose malicious ml models, 2025.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Jfrog and hugging face join forces to expose malicious ml models, 2025

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.542181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a3750f84-319e-4f43-b66f-96076fa96c0c · outbound

This paper cites Adversarial attacks on cooperative multi-agent deep reinforcement learning: A dynamic group-based adversarial example transferability method.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Adversarial attacks on cooperative multi-agent deep reinforcement learning: A dynamic group-based adversarial example transferability method

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.405740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 562d4d23-1d41-48c9-af6d-89ac88f74ac8 · outbound

This paper cites Auto- matic grouping for efficient cooperative multi-agent reinforcement learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Auto- matic grouping for efficient cooperative multi-agent reinforcement learning

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.237305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 67b537c5-4696-4557-8069-6ad9909ae02c · outbound

This paper cites Backdoorl: Backdoor attack against competitive reinforcement learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Backdoorl: Backdoor attack against competitive reinforcement learning

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:43.125961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 12071fff-309c-47ef-a630-aa4d4e42adb9 · outbound

This paper cites Group-aware coordination graph for multi-agent rein- forcement learning.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Group-aware coordination graph for multi-agent rein- forcement learning

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:42.974108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5dc1ec11-4304-49f3-863a-5bbe4957fdb8 · outbound

This paper cites Pan, Shuyi Yang, Lakshya A.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Pan, Shuyi Yang, Lakshya A

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:42.847512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 98658d58-5c04-4dca-af28-fe425ed763f0 · outbound

This paper cites Kwon, Makoto Onizuka, Shaojie Tang, and Chuan Xiao.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Kwon, Makoto Onizuka, Shaojie Tang, and Chuan Xiao

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:42.698003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4dc71cd3-6dc5-488b-8fde-c3c63af5ef08 · outbound

This paper cites Certifiably robust policy learning against adversarial multi-agent communication.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Certifiably robust policy learning against adversarial multi-agent communication

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:36.278584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acbb6996-6195-430c-928e-aee457bd501e · outbound

This paper cites T2mac: targeted and trusted multi-agent communication through selective engagement and evidence-driven integration.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems T2mac: targeted and trusted multi-agent communication through selective engagement and evidence-driven integration

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:42.531983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0444f131-5e31-43dd-afb6-2562e1c98cfc · outbound

This paper cites BlockAgents: Towards byzan- tine–robust llm–based multi–agent coordination via blockchain.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems BlockAgents: Towards byzan- tine–robust llm–based multi–agent coordination via blockchain

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:05:42.366433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8216c338-629b-49e6-920c-0a84b31ef8ad · outbound

This paper cites Autogen: Enabling next-gen llm applications via multi-agent conversation, 2023.

Seven Security Challenges in Cross-domain Multi-agent LLM Systems Autogen: Enabling next-gen llm applications via multi-agent conversation, 2023

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:36.436653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2915ae9e-bd2d-430b-8003-bbd5263a619d · inbound

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

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-29T02:14:01.661949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b8382a21-5ab8-4358-8333-eb5e825dbb01 · inbound

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey cites this paper.

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:26:33.416300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24904a41-cf8d-4242-a026-a9cf68b7b0be · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 109

Resolution: verified exact; arxiv_id, observed 2026-06-29T02:14:01.661949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e16ad482-d1cd-4192-98d5-c30e8fbbcfa6 · inbound

AI Agents with Decentralized Identifiers and Verifiable Credentials cites this paper.

AI Agents with Decentralized Identifiers and Verifiable Credentials Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T13:26:46.211876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2668b3d-c34a-4594-ad7a-086a3857165a · inbound

SoK: Security of Autonomous LLM Agents in Agentic Commerce cites this paper.

SoK: Security of Autonomous LLM Agents in Agentic Commerce Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-06-29T02:14:01.661949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a08e440f-48d7-48c4-b0bc-3dc98b810d00 · inbound

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-06-29T02:14:01.661949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 05eb9c01-18bf-4b82-956d-6863ac98f1fd · inbound

Agent Security Needs Redefinition through a Holistic Framework cites this paper.

Agent Security Needs Redefinition through a Holistic Framework Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 213

Resolution: unresolved; no resolver link, observed 2026-08-01T06:04:46.337829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aeaa6cf-7ac2-4189-9985-d34b853d03c6 · inbound

From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems cites this paper.

From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems Seven Security Challenges in Cross-domain Multi-agent LLM Systems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T01:03:45.269216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.