AI Control: Improving Safety Despite Intentional Subversion | Paper Citation Record

Observation 56058db1-e979-4b2c-862e-a32b97257ba5 · inbound

Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation cites this paper.

Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation AI Control: Improving Safety Despite Intentional Subversion

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T18:31:14.158845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58d6d5d9-4759-4f46-84ac-428afd55a46c · inbound

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management cites this paper.

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management AI Control: Improving Safety Despite Intentional Subversion

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T14:48:44.440069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62406f3f-8d92-4d13-9b40-ac547bef0427 · inbound

Learning Safety Constraints for Large Language Models cites this paper.

Learning Safety Constraints for Large Language Models AI Control: Improving Safety Despite Intentional Subversion

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T12:30:15.698528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee9e0b3-3fdd-4e45-a4b6-3791648bdc1f · inbound

Systematic Hazard Analysis for Frontier AI using STPA cites this paper.

Systematic Hazard Analysis for Frontier AI using STPA AI Control: Improving Safety Despite Intentional Subversion

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:38:04.134407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3811c15b-4fce-40af-af94-5b024e4c88ba · inbound

To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems cites this paper.

To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems AI Control: Improving Safety Despite Intentional Subversion

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:32:17.342323Z

Source-reported events for the cited work

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

Observation c75cd383-58c4-4964-8eca-3ea296dfcb39 · inbound

Adversarial Attacks on Robotic Vision Language Action Models cites this paper.

Adversarial Attacks on Robotic Vision Language Action Models AI Control: Improving Safety Despite Intentional Subversion

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:11:40.307636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e61b53ec-69d8-4bec-8588-19b1ebf02a2b · inbound

A Red Teaming Roadmap Towards System-Level Safety cites this paper.

A Red Teaming Roadmap Towards System-Level Safety AI Control: Improving Safety Despite Intentional Subversion

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:11:19.176489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 171bc1d9-efa4-4d45-85cc-b610962d7f10 · inbound

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values cites this paper.

Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values AI Control: Improving Safety Despite Intentional Subversion

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:43:07.278246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab12fc43-486f-4daa-bac5-8049aee7dcf1 · inbound

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) cites this paper.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) AI Control: Improving Safety Despite Intentional Subversion

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:26:57.283865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6511c20f-7a93-40c4-b169-2f85f00cba12 · inbound

Subversion via Focal Points: Investigating Collusion in LLM Monitoring cites this paper.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring AI Control: Improving Safety Despite Intentional Subversion

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.430622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce29ce03-2324-465c-84a3-bcc948022b44 · inbound

Towards Measurement Theory for Artificial Intelligence cites this paper.

Towards Measurement Theory for Artificial Intelligence AI Control: Improving Safety Despite Intentional Subversion

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:27:33.196672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdba531b-0cde-4c13-b6f1-c526f77578c9 · inbound

The bitter lesson of misuse detection cites this paper.

The bitter lesson of misuse detection AI Control: Improving Safety Despite Intentional Subversion

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:18:40.580182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a61a6d-dca5-4933-8d5b-37778dd21446 · inbound

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models cites this paper.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models AI Control: Improving Safety Despite Intentional Subversion

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.995530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 319fba47-17c7-4813-9d53-370ada5c8e78 · inbound

Investigating Crossing Perception in 3D Graph Visualisation cites this paper.

Investigating Crossing Perception in 3D Graph Visualisation AI Control: Improving Safety Despite Intentional Subversion

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T10:22:55.800253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68cc17b8-adda-4376-bcc8-23d1f798ffc3 · inbound

Reliable Weak-to-Strong Monitoring of LLM Agents cites this paper.

Reliable Weak-to-Strong Monitoring of LLM Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T15:53:49.397384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99166c4d-a50d-4b60-8e9e-6240a4da226a · inbound

NEST: Nascent Encoded Steganographic Thoughts cites this paper.

NEST: Nascent Encoded Steganographic Thoughts AI Control: Improving Safety Despite Intentional Subversion

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T23:21:32.317208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d90a3a-5b31-448d-826b-c405c9aaa3ac · inbound

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability cites this paper.

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability AI Control: Improving Safety Despite Intentional Subversion

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T22:48:22.975610Z

Source-reported events for the cited work

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

Observation a3b4a598-2138-491b-b663-57008d050bb5 · inbound

TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol cites this paper.

TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol AI Control: Improving Safety Despite Intentional Subversion

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T11:41:46.131575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01c8868e-6d6e-4843-bb2b-b98d861f58f2 · inbound

Detecting Safety Violations Across Many Agent Traces cites this paper.

Detecting Safety Violations Across Many Agent Traces AI Control: Improving Safety Despite Intentional Subversion

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T21:20:52.795352Z

Source-reported events for the cited work

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

Observation b2e5325a-4b53-44b5-a717-93cb8c4cdc0e · inbound

Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6 cites this paper.

Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6 AI Control: Improving Safety Despite Intentional Subversion

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-15T08:35:19.300181Z

Source-reported events for the cited work

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

Observation 3838f414-d5da-4cf9-bfa6-7abff81c1ba1 · inbound

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems cites this paper.

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems AI Control: Improving Safety Despite Intentional Subversion

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:28:39.099656Z

Source-reported events for the cited work

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

Observation 9471e4d9-9796-4e58-9cfa-2046ce6c6c6e · inbound

ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data cites this paper.

ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data AI Control: Improving Safety Despite Intentional Subversion

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:56:10.985688Z

Source-reported events for the cited work

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

Observation bcad1dac-5128-4161-9b99-b3d046604445 · inbound

Estimating Tail Risks in Language Model Output Distributions cites this paper.

Estimating Tail Risks in Language Model Output Distributions AI Control: Improving Safety Despite Intentional Subversion

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:16:08.142882Z

Source-reported events for the cited work

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

Observation 4a94edb4-7645-49b7-b1b2-242218782e9e · inbound

Risk Reporting for Developers' Internal AI Model Use cites this paper.

Risk Reporting for Developers' Internal AI Model Use AI Control: Improving Safety Despite Intentional Subversion

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:16:16.810684Z

Source-reported events for the cited work

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

Observation 8a47d8b9-ae9d-4b04-9b44-ea27e042e8cf · inbound

Automated alignment is harder than you think cites this paper.

Automated alignment is harder than you think AI Control: Improving Safety Despite Intentional Subversion

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:10.157741Z

Source-reported events for the cited work

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

Observation 121cd7ad-b89d-4e29-a212-ebf9b5346617 · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety AI Control: Improving Safety Despite Intentional Subversion

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:51:07.940397Z

Source-reported events for the cited work

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

Observation 1ae322a6-a659-413e-8b5e-f6e772c49926 · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety AI Control: Improving Safety Despite Intentional Subversion

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:06:42.857383Z

Source-reported events for the cited work

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

Observation b1ea782d-195a-4483-aa0d-7b2de7c793fe · inbound

Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems cites this paper.

Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems AI Control: Improving Safety Despite Intentional Subversion

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:29:59.632637Z

Source-reported events for the cited work

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

Observation d55c12cd-22ac-4e05-86b7-2c42c2763fb5 · inbound

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning cites this paper.

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning AI Control: Improving Safety Despite Intentional Subversion

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-06-30T15:34:48.019328Z

Source-reported events for the cited work

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

Observation 47bb62e4-2c29-4758-b8c1-cbe4fa99cf4a · inbound

AI Integrity: Defending Against Backdoors and Secret Loyalties cites this paper.

AI Integrity: Defending Against Backdoors and Secret Loyalties AI Control: Improving Safety Despite Intentional Subversion

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T14:59:54.643757Z

Source-reported events for the cited work

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

Observation 0b7bb4b9-9f84-4cb1-9e51-fa515ead3f77 · inbound

Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling cites this paper.

Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling AI Control: Improving Safety Despite Intentional Subversion

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:16:24.582255Z

Source-reported events for the cited work

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

Observation b6802ae8-8481-4060-bb5d-272673ad8924 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model AI Control: Improving Safety Despite Intentional Subversion

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:05:47.124671Z

Source-reported events for the cited work

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

Observation 65be4607-7185-4b38-b2e8-c593527d6f27 · inbound

Temporal Preference Concepts and their Functions in a Large Language Model cites this paper.

Temporal Preference Concepts and their Functions in a Large Language Model AI Control: Improving Safety Despite Intentional Subversion

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T17:03:44.315006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79ec6dc4-84aa-44a7-9073-31b257e5b5b3 · inbound

A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing cites this paper.

A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing AI Control: Improving Safety Despite Intentional Subversion

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-07-02T08:16:47.565397Z

Source-reported events for the cited work

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

Observation 57645995-3d94-4668-9cc4-c0cac1a03d0c · inbound

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents cites this paper.

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T17:07:12.748737Z

Source-reported events for the cited work

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

Observation 81c34412-a419-4955-acf7-384e675bfbd2 · inbound

The Distributed Detectability Band Against Marginal-Preserving Attacks cites this paper.

The Distributed Detectability Band Against Marginal-Preserving Attacks AI Control: Improving Safety Despite Intentional Subversion

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:57:41.863875Z

Source-reported events for the cited work

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

Observation 478e43f2-a038-493c-9bc1-047ce3c342db · inbound

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms cites this paper.

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms AI Control: Improving Safety Despite Intentional Subversion

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.296740Z

Source-reported events for the cited work

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

Observation f90f6bfe-30d3-41f1-82d4-0a6db6d86e14 · inbound

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems cites this paper.

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems AI Control: Improving Safety Despite Intentional Subversion

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T16:15:50.222877Z

Source-reported events for the cited work

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

Observation db9b77e0-160e-4860-bd4e-4fc46418e204 · inbound

Online Safety Monitoring for LLMs cites this paper.

Online Safety Monitoring for LLMs AI Control: Improving Safety Despite Intentional Subversion

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-03T12:58:07.488126Z

Source-reported events for the cited work

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

Observation e4e7d8dc-ac18-43b1-a7dc-ca15667e423d · inbound

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages cites this paper.

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages AI Control: Improving Safety Despite Intentional Subversion

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T04:00:44.072640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 763b59fa-e211-41c2-96fb-65078c47324f · inbound

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages cites this paper.

Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages AI Control: Improving Safety Despite Intentional Subversion

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T08:31:14.785797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79439b91-bf29-490d-b568-a651c6184055 · inbound

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents cites this paper.

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-10T18:37:31.158825Z

Source-reported events for the cited work

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

Observation 9401af59-69f5-44bf-9c14-9fa2d3c67436 · inbound

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents cites this paper.

ScopeJudge: Cost-Aware Pre-Execution Gating for Offensive Security Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T00:49:46.954375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd8cd22c-d745-4bb6-be33-69863c55f995 · inbound

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring cites this paper.

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring AI Control: Improving Safety Despite Intentional Subversion

Reference 87

Resolution: verified exact; local_arxiv, observed 2026-07-10T00:56:41.075656Z

Source-reported events for the cited work

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

Observation b6f05b4e-2134-4ea0-b1a8-32bde78b494b · inbound

GDM AI Control Roadmap cites this paper.

GDM AI Control Roadmap AI Control: Improving Safety Despite Intentional Subversion

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T06:53:51.953667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 568a96db-126c-4bad-940b-7a630e2c6074 · inbound

Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives cites this paper.

Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives AI Control: Improving Safety Despite Intentional Subversion

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T05:14:54.057238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aec30b4-4ff6-4a7c-ace2-d681684cb965 · inbound

Democratizing Agent Deployment Safety: A Structural Monitoring Approach cites this paper.

Democratizing Agent Deployment Safety: A Structural Monitoring Approach AI Control: Improving Safety Despite Intentional Subversion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:47:11.743438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d38789b5-9a42-4d64-a416-229fdcf8eb46 · inbound

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D cites this paper.

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D AI Control: Improving Safety Despite Intentional Subversion

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T12:49:57.527663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85258d82-146b-4d7f-a9a2-c0777fb33a3c · inbound

Code Monitor Red Teaming for Public-Test-Passing Code cites this paper.

Code Monitor Red Teaming for Public-Test-Passing Code AI Control: Improving Safety Despite Intentional Subversion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T09:12:25.068962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 777c2d43-5634-4cbb-84bf-9866060db016 · inbound

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents cites this paper.

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T00:13:37.456860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725e6c89-5343-40d3-b6a0-1ac7c27400f8 · inbound

One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence cites this paper.

One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence AI Control: Improving Safety Despite Intentional Subversion

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T11:29:22.444200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea43ee38-bee8-4063-a38c-75ce56b4ed8f · inbound

Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents cites this paper.

Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents AI Control: Improving Safety Despite Intentional Subversion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:47:58.574890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers