Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-10T20:55:21.031591Z
Paper Citation Record · LEDGER
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
As of 15 August 2026, this Paper Citation Record lists 79 of 79 outbound references and 0 inbound Pith citation observations for arXiv:2607.06807.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
79 of 79 outbound references displayed
- verified exact2
- verified fuzzy37
- unresolved5
- parse uncertain0
- malformed identifier0
- metadata mismatch35
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 96788680-c4c1-4db7-8808-e02a60b70f6c · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Gemini: A Family of Highly Capable Multimodal Models
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.995323Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ac7258ce-13a5-4b1f-afb2-b9be6f1ba4c1 · outbound
This paper cites Qwen Technical Report.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Qwen Technical Report
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:35.029686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b276e316-fdb6-4c6d-98ae-cc019be49b72 · outbound
This paper cites DeepSeek-V3 Technical Report.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems DeepSeek-V3 Technical Report
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.828909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ff2b41a1-8d09-4d1d-b67a-523acb272037 · outbound
This paper cites Frontiers of Computer Science , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Frontiers of Computer Science , volume=
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.968241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation d3be19a4-7216-4ba6-a281-2919442ef2e2 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.914835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 87a92a94-adc6-4ae9-a189-0a8493770a5c · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Advances in Neural Information Processing Systems , volume=
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.937825Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation cbc9cc4c-73a1-4fc3-8b88-e49e4362b092 · outbound
This paper cites Forty-first International Conference on Machine Learning , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Forty-first International Conference on Machine Learning , year=
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.537088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6bfcbace-c70b-442f-a65c-aed5ad95e5ba · outbound
This paper cites Scaling Large Language Model-based Multi-Agent Collaboration.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Scaling Large Language Model-based Multi-Agent Collaboration
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.580097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4b0e31d7-37d7-4263-b851-d33160c57eae · outbound
This paper cites author=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems author=
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.652640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 2957c9cd-ab30-4d67-85c2-1c1fcf7162b1 · outbound
This paper cites Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.220087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b985f25c-b7c3-46ca-9007-06eadf48fdb2 · outbound
This paper cites 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.229297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation fbf3cfad-54c3-4069-871a-63b61fc40a6a · outbound
This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Reference 12
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.622539Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5ab3aae1-2637-44a4-9263-91c0d68b1018 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.969333Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a6478b69-8110-4f00-9e8e-b95600c45bc3 · outbound
This paper cites RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.974946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e57bf030-f21d-445d-82d9-05dc65abec5c · outbound
This paper cites Findings of the Association for Computational Linguistics ACL 2024 , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Findings of the Association for Computational Linguistics ACL 2024 , pages=
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.000678Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a19b7883-5357-4b5f-a4de-341be8b0f687 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Advances in Neural Information Processing Systems , volume=
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.895527Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4378fb33-7fba-4141-8afe-b42e1254040a · outbound
This paper cites Get my drift? Catching LLM Task Drift with Activation Deltas.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Get my drift? Catching LLM Task Drift with Activation Deltas
Reference 17
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.851213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 84cdd8e4-2e1a-4b30-8360-17e31f7ae762 · outbound
This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.919538Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e6e9c041-3718-4108-b816-5722b6a777f5 · outbound
This paper cites JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
Reference 19
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.916124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation d3520720-f9ab-4df1-9c89-01ffc474de57 · outbound
This paper cites an unresolved cited work.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-07-10T20:57:35.945343Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation fe3a04f6-c054-4b93-a85e-4153e2764802 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Training Verifiers to Solve Math Word Problems
Reference 21
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.602027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 46fca5ae-73f9-4b92-aa0a-047196f9be9c · outbound
This paper cites DynTaskMAS : A dynamic task graph-driven framework for asynchronous and parallel LLM -based multi-agent systems.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems DynTaskMAS : A dynamic task graph-driven framework for asynchronous and parallel LLM -based multi-agent systems
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-10T20:57:34.936792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a8d4ac11-f435-43a4-9d19-38ded621310a · outbound
This paper cites Proceedings of the 2018 conference on empirical methods in natural language processing , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 2018 conference on empirical methods in natural language processing , pages=
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.723234Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8bda52b4-e1b4-4c1a-97ea-5d1310db6adc · outbound
This paper cites 2024 , howpublished=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems 2024 , howpublished=
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.482312Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5f5c1104-68af-46c4-bea8-72f9b4890319 · outbound
This paper cites International Conference on Learning Representations , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems International Conference on Learning Representations , volume=
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.181817Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ccce45c3-51d7-4d18-99ba-10bb5371be01 · outbound
This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.810777Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6f4e7cd1-3f79-46e1-8ab2-e935cf7c5ff1 · outbound
This paper cites Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
Reference 27
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.883304Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 772890eb-75f7-4074-9888-d8b4b0e57a91 · outbound
This paper cites RouteLLM: Learning to Route LLMs with Preference Data.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems RouteLLM: Learning to Route LLMs with Preference Data
Reference 28
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.947178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T07:08:14.190615+00:00.
Observation 93aa2cbc-5f67-4cc9-a142-67b536c7c75b · outbound
This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
Reference 29
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.673701Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T07:08:14.020381+00:00.
Observation ad429d00-f485-4bdb-85ab-4adfe68a762a · outbound
This paper cites Machine learning , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Machine learning , volume=
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.603546Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 639dbf85-d9cd-4cc5-981a-a0dd4faf9943 · outbound
This paper cites Computers & Security , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Computers & Security , volume=
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.211960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 32180d9f-8008-4054-9028-bda119840acf · outbound
This paper cites European Conference on Information Retrieval , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems European Conference on Information Retrieval , pages=
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.518444Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 97a1f0f7-707b-419b-8870-b25bef562b49 · outbound
This paper cites Qwen3 Technical Report.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Qwen3 Technical Report
Reference 33
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.578609Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation eb085aae-4de5-42e9-88d6-c0a71186b60e · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems LLaMA: Open and Efficient Foundation Language Models
Reference 34
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.716115Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5007da1d-d93f-4207-ade5-9b27fc54f98c · outbound
This paper cites gpt-oss-120b & gpt-oss-20b Model Card.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems gpt-oss-120b & gpt-oss-20b Model Card
Reference 35
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.732983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 1f0dbe6e-48ba-411c-b5aa-3e00b93800f4 · outbound
This paper cites International conference on machine learning , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems International conference on machine learning , pages=
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.894048Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 59c9a12f-7d7b-4c49-b161-f9a441c4f900 · outbound
This paper cites Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto
Reference 37
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-10T20:57:34.618765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8498b9a2-783a-42af-a588-a4f42146d381 · outbound
This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.021153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a4f8249c-778a-4485-b6fd-04502f4c4d7d · outbound
This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reference 39
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.831848Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation bc218119-2b26-42b5-b438-2785c361117b · outbound
This paper cites CoRR , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems CoRR , year=
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.791875Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 353d667a-60b1-40a1-9553-c806d75f3ee2 · outbound
This paper cites BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
Reference 41
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.895863Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 3ad51200-cecc-4b01-9970-597a8073d419 · outbound
This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Reference 42
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.967267Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0c45dc3c-de5d-4392-bb25-9cb66b9c5988 · outbound
This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.761375Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6158eaf3-4304-489f-9535-a3edfadc9e6f · outbound
This paper cites ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
Reference 44
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.676550Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 7952af6e-b8fc-4efd-b145-9f88c424643d · outbound
This paper cites NetSafe: Exploring the Topological Safety of Multi-agent Networks.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems NetSafe: Exploring the Topological Safety of Multi-agent Networks
Reference 45
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.955947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 98530c8e-0028-407a-97b7-c06aef7814a6 · outbound
This paper cites AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management
Reference 46
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:35.010016Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6bf9402b-c279-4327-8b45-60adb90a03de · outbound
This paper cites To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Reference 47
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.711526Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 93a17037-9778-4e16-9707-cf053bf1762b · outbound
This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
Reference 48
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.477702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 321f68f8-c1a3-4cef-8c88-dbd02a0ef42f · outbound
This paper cites Proceedings of the 41st International Conference on Machine Learning , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 41st International Conference on Machine Learning , pages=
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.857734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 365bbf48-02d5-46f0-a15b-2f4c58dec515 · outbound
This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.174160Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6ac94365-f39f-404a-9f39-e5e449603e18 · outbound
This paper cites The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
Reference 51
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.794177Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 85d9a114-59d5-43d3-84df-2809fe9704a6 · outbound
This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Findings of the Association for Computational Linguistics: ACL 2025 , pages=
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.693133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 781349bf-0d3e-448f-853e-5b81caaf5c90 · outbound
This paper cites MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework
Reference 53
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.420095Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6660901d-8185-4d8e-98a3-eb2e2e5497c2 · outbound
This paper cites CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
Reference 54
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.516433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0b5adbac-d96e-40f3-9d41-9199e0a12384 · outbound
This paper cites arXiv preprint arXiv:2504.00218 , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems arXiv preprint arXiv:2504.00218 , year=
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-07-10T20:57:34.986010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e97679e3-2fbd-4dbb-9ea3-8b1432a727d3 · outbound
This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Evil Geniuses: Delving into the Safety of LLM-based Agents
Reference 56
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.640349Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4757c623-4dc7-40e2-9b41-1c2f4c92c554 · outbound
This paper cites Prompt Injection attack against LLM-integrated Applications.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Prompt Injection attack against LLM-integrated Applications
Reference 57
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.791596Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e7c56370-d53c-496a-a2c0-1cccdb746ec2 · outbound
This paper cites First Conference on Language Modeling , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems First Conference on Language Modeling , year=
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.741634Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5da83382-3df8-4c5a-aaf7-c5aa91567828 · outbound
This paper cites Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
Reference 59
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.378672Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation dcbf6041-11e0-4685-86eb-13feedf545d8 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the AAAI Conference on Artificial Intelligence , volume=
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.201393Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c18d4442-0df3-4f2c-97e6-b9dea02779ee · outbound
This paper cites an unresolved cited work.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Unresolved cited work
Reference 61
- Resolution
- unresolved
- raw_fallback, observed 2026-07-10T20:57:36.101515Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5a59725c-5db6-4df6-8a3d-29cf77131395 · outbound
This paper cites an unresolved cited work.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Unresolved cited work
Reference 62
- Resolution
- unresolved
- raw_fallback, observed 2026-07-10T20:57:35.812605Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e6bab736-a335-4b58-af68-e75101e2c6f4 · outbound
This paper cites Large Language Model for Participatory Urban Planning.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Large Language Model for Participatory Urban Planning
Reference 63
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.658027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 46ff4a73-d4c3-400b-a725-a5d50027237c · outbound
This paper cites Forty-first International Conference on Machine Learning , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Forty-first International Conference on Machine Learning , year=
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.732928Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c8df579f-deee-47f6-8fbf-15771e9f4fbf · outbound
This paper cites Proceedings of the 2024 conference on empirical methods in natural language processing , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the 2024 conference on empirical methods in natural language processing , pages=
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.150619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation cc6ffbf2-7af3-42c4-8f0e-8647a82fb78a · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Advances in Neural Information Processing Systems , volume=
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.755585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 6816b258-4640-4cef-a02e-4e56f57bd002 · outbound
This paper cites International Conference on Learning Representations , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems International Conference on Learning Representations , volume=
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.124849Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 124c36e0-98f4-4f90-a407-90f1939d1605 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Advances in Neural Information Processing Systems , volume=
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.194167Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4be6e1ec-8e57-49db-a1d2-c2cf32f1cb06 · outbound
This paper cites 2023 IEEE International Conference on Data Mining (ICDM) , year=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems 2023 IEEE International Conference on Data Mining (ICDM) , year=
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.161683Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b00b1bde-ad4b-4ea9-9df8-ea3af2c07c2d · outbound
This paper cites an unresolved cited work.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Unresolved cited work
Reference 70
- Resolution
- unresolved
- raw_fallback, observed 2026-07-10T20:57:36.079001Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation cec6a989-10fc-49e7-b3a5-11983b085f6b · outbound
This paper cites , author=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems , author=
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.023043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation fc2df9e2-f8fc-4617-bc11-395765a58e6e · outbound
This paper cites an unresolved cited work.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Unresolved cited work
Reference 72
- Resolution
- unresolved
- raw_fallback, observed 2026-07-10T20:57:36.051407Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation d95dc51a-1ab4-412d-a391-418669950e9d · outbound
This paper cites MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-07-10T20:57:34.461963Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5b2a31db-111b-4d64-a1c8-198d2506288c · outbound
This paper cites Multi-agent Architecture Search via Agentic Supernet.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Multi-agent Architecture Search via Agentic Supernet
Reference 74
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.694548Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8fcc7553-0acd-40c6-9583-6dfc4affe828 · outbound
This paper cites AFlow: Automating Agentic Workflow Generation.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems AFlow: Automating Agentic Workflow Generation
Reference 75
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.906236Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 940d5ae8-7013-4b98-997c-f90de31fc713 · outbound
This paper cites ICPR , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems ICPR , pages=
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.834384Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation f0735b64-a0ab-4127-97fc-cb3e41555077 · outbound
This paper cites Sensors , volume=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Sensors , volume=
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:35.682714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation dcc6986a-47b0-47d3-b7e4-f8f63fae48b9 · outbound
This paper cites Proceedings of the IEEE conference on computer vision and pattern recognition , pages=.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-10T20:57:36.126079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5b6114b8-3d60-4d89-9034-5b3a49d97c3f · outbound
This paper cites Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS.
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Reference 79
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-10T20:57:34.810598Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Pith citing papers
No inbound Pith citation observations are available.