Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents | Paper Citation Record

Observation d7448029-fd2b-46b8-8f01-bbf7ad43d487 · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.964497Z

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 a63e0232-3732-49d0-9208-c68909232097 · outbound

This paper cites Arora, S.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Arora, S

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.968973Z

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 11199b3f-40b2-4b92-a653-44732c62ff5b · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.997040Z

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 6457398a-7e11-4d66-841d-cf2780bdb754 · outbound

This paper cites RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.973932Z

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 f7055d05-e992-49c0-854f-8125434520f9 · outbound

This paper cites Bordes, C.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Bordes, C

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.991937Z

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 4b9fdf3f-7778-40d7-9dd2-9f12810ad2a9 · outbound

This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.001946Z

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 97325393-fe10-40ab-8464-4e60c294076c · outbound

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

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.931932Z

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 2cbda156-ec48-46de-92e9-fed450dadf5a · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.924885Z

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 317b4b9f-2ad6-44b5-87e3-6709fa52abb7 · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.937545Z

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 e25cc844-6f5a-4aa3-a9b8-e4b14881adfc · outbound

This paper cites Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Yann Dubois, Balázs Galambosi, Percy Liang, and Tat- sunori B Hashimoto

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.942984Z

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 f3d770a8-7c0d-42e7-bb3a-150ffd0b512d · outbound

This paper cites Agentleak: A full-stack benchmark for privacy leakage in multi-agent llm systems.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agentleak: A full-stack benchmark for privacy leakage in multi-agent llm systems

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.913592Z

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 7ffffaaa-f023-4b25-9ec1-55900731891a · outbound

This paper cites WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.902195Z

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 04461fc8-bafd-4be1-9322-7842dff66de3 · outbound

This paper cites Backdooragent: A unified framework for backdoor attacks on llm-based agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Backdooragent: A unified framework for backdoor attacks on llm-based agents

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.880888Z

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 85b0d4e7-a8a2-42ee-86d0-03b4d12aa8f5 · outbound

This paper cites RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.870990Z

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 853c3ada-9d65-4089-9c8a-cfeaece0b7a2 · outbound

This paper cites Alignment faking in large language models.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Alignment faking in large language models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.885882Z

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 b32ee26c-2bd6-4fec-9609-431acca58607 · outbound

This paper cites Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.875654Z

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 4e9279dc-b024-4673-880b-171ed4c94d20 · outbound

This paper cites Hadeliya, M.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Hadeliya, M

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.907448Z

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 509f0dc6-de5c-46f4-b529-ff370c2b0f9d · outbound

This paper cites Multi-Agent Risks from Advanced AI.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Multi-Agent Risks from Advanced AI

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.982090Z

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 56f9752d-e8a3-4b38-84f7-a6f74d7b8cd7 · outbound

This paper cites Hopman, J.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Hopman, J

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.833946Z

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 a7fbe2f2-f1cf-40bb-ac9d-29c6534da786 · outbound

This paper cites TrustAgent: Towards Safe and Trustworthy LLM-based Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents TrustAgent: Towards Safe and Trustworthy LLM-based Agents

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.839185Z

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 86227a48-bf0a-49a8-828e-3d27de4fa793 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.828334Z

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 594844c5-4a6c-4666-baa5-72e0b5f1fc29 · outbound

This paper cites Jiang, Y.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Jiang, Y

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.844416Z

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 f6a8b501-c52d-49cb-a0c3-d818f5b7d17f · outbound

This paper cites Juneja, J.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Juneja, J

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.818083Z

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 323dda98-9909-4554-bd9a-ebe310de255c · outbound

This paper cites Kavathekar, H.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Kavathekar, H

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.801027Z

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 c6157c38-f118-4488-965b-126a0e324d1a · outbound

This paper cites SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.805773Z

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 68b27e3c-0afc-42c0-997f-a0fff24e7e37 · outbound

This paper cites Bradley Knox, and Kimin Lee.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Bradley Knox, and Kimin Lee

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.812705Z

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 fccabdc4-e26a-4a40-8ad7-a2d8392829cf · outbound

This paper cites ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-05T02:16:16.756993Z

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 7b1a9fd3-3093-4323-8df2-f34968cf18c4 · outbound

This paper cites A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.891144Z

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 cff8d4f4-6bba-42b0-a4bf-9a0969f32cca · outbound

This paper cites SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.639271Z

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 d963c482-fd03-4cc5-8179-dcf80d320a36 · outbound

This paper cites Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agentsafe: Benchmarking the safety of embodied agents on hazardous instructions

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.644461Z

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 393ab57d-bca6-42ba-8cc7-9a0f32feb5de · outbound

This paper cites Is- bench: Evaluating interactive safety of vlm-driven embodied agents in daily household tasks.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Is- bench: Evaluating interactive safety of vlm-driven embodied agents in daily household tasks

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.007268Z

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 0ae9007d-334b-4abd-b96b-75870300796d · outbound

This paper cites Agentauditor: Human-level safety and security evaluation for llm agents.arXiv preprint arXiv:2506.00641.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agentauditor: Human-level safety and security evaluation for llm agents.arXiv preprint arXiv:2506.00641

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.012454Z

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 c1eafb32-4e8a-4616-bc67-c910bcde6c26 · outbound

This paper cites Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.823188Z

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 e7318f8f-69f2-489e-a78a-6ef3d401c1fe · outbound

This paper cites Natural Emergent Misalignment from Reward Hacking in Production RL.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Natural Emergent Misalignment from Reward Hacking in Production RL

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.655093Z

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 102ae941-79ac-43c2-8907-e5b90e58b0f3 · outbound

This paper cites McGregor, V.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents McGregor, V

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.860696Z

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 bc03938c-acf7-4e92-8a54-1d47d8a45a91 · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Frontier Models are Capable of In-context Scheming

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.790333Z

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 f0295ea1-fa65-467c-be28-0d8d34d5f688 · outbound

This paper cites an unresolved cited work.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-21T01:43:57.213984Z

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 b79c7602-7f7c-4d27-a357-45e108c435fa · outbound

This paper cites Evaluation and Benchmarking of LLM Agents: A Survey.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Evaluation and Benchmarking of LLM Agents: A Survey

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.680558Z

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 fc1e67d8-bf15-4319-a5e5-da783eb72ca5 · outbound

This paper cites AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-23T04:13:38.836403Z

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 e94a4214-ee0a-462d-b4cb-42256b2cd592 · outbound

This paper cites Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:14.756178Z

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 869c3a57-64a1-4ff9-ae17-3ec45f6b8da3 · outbound

This paper cites N \"o ther, A.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents N \"o ther, A

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.035744Z

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 e8a3e7e2-a852-48ae-8c54-3e7a98dff719 · outbound

This paper cites Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.709741Z

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 5a9e2519-e0b9-4629-aa8f-4bf3ca85ff2b · outbound

This paper cites When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.736724Z

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 905caca1-94da-40e4-9adc-a3a18b023ce9 · outbound

This paper cites Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.649657Z

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 8fc44ee4-99b8-476f-860e-7e8645fc0122 · outbound

This paper cites BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.704660Z

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 aa9ecd7e-3111-4372-8f79-b5d03991a1df · outbound

This paper cites Identifying the Risks of LM Agents with an LM-Emulated Sandbox.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.692475Z

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 c36f65e9-2496-45e3-bd1c-e9d03e27654a · outbound

This paper cites Schlatter, B.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Schlatter, B

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.700164Z

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 919ac7ed-ea23-413a-b3c7-9eb712fe5cfb · outbound

This paper cites PropensityBench: Evaluating propensity under pressure.arXiv preprint arXiv:2511.20703.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents PropensityBench: Evaluating propensity under pressure.arXiv preprint arXiv:2511.20703

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.855920Z

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 6c0c96f1-3b89-4fd2-837e-27a291dffcfe · outbound

This paper cites an unresolved cited work.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Unresolved cited work

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.762811Z

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 bef34a4a-98b5-41f4-847a-44179fde9bcb · outbound

This paper cites Vijayvargiya, A.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Vijayvargiya, A

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.953464Z

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 061f3076-96ea-4941-bda7-b4a3b59a52aa · outbound

This paper cites AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:57.021306Z

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 9a3344e2-5e67-4e03-bc5a-0669f6456152 · outbound

This paper cites A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.850450Z

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 9465a880-24f8-4a52-90af-93158c92b1b1 · outbound

This paper cites A Survey on Large Language Model based Autonomous Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents A Survey on Large Language Model based Autonomous Agents

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.717642Z

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 c24b1e4b-2cb1-4fa4-a55c-6cb45de64082 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.725147Z

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 e1ef2c08-0e70-4678-b327-3718a55b296e · outbound

This paper cites SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.686578Z

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 3dc32d50-682f-4799-860e-6f84d6ceb9db · outbound

This paper cites GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:57:50.455179Z

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 6792b4dd-5bfc-41f9-95a2-70c74ecb788f · outbound

This paper cites an unresolved cited work.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-21T01:43:57.210432Z

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 907bf584-306e-46bd-b3cc-2a95e6a32d88 · outbound

This paper cites Survey on Evaluation of LLM-based Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Survey on Evaluation of LLM-based Agents

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.713747Z

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 87a7a443-e182-4e75-b277-cc4a36b9f1e9 · outbound

This paper cites SafeAgentBench: A benchmark for safe task planning of embodied LLM agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents SafeAgentBench: A benchmark for safe task planning of embodied LLM agents

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.742827Z

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 8b25fa8c-80dd-4d2a-96df-b8eab9b2499c · outbound

This paper cites How Should AI Safety Benchmarks Benchmark Safety?.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents How Should AI Safety Benchmarks Benchmark Safety?

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-08-06T02:07:04.187677Z

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 6afe3eec-e3fa-4324-b7c2-178e295152dc · outbound

This paper cites A Survey on Trustworthy LLM Agents: Threats and Countermeasures.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents A Survey on Trustworthy LLM Agents: Threats and Countermeasures

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.947706Z

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 967c5c0a-2f0d-4fd8-b5e8-bcd54bff5ea2 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.667888Z

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 273019c1-ba34-48ec-a485-1e7b818939f6 · outbound

This paper cites Nothing humbles you like telling your OpenClaw ``confirm before acting'' and watching it speedrun deleting your inbox.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Nothing humbles you like telling your OpenClaw ``confirm before acting'' and watching it speedrun deleting your inbox

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.919539Z

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 c4f743fa-3509-46c5-afde-7f86ab5ef670 · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.987491Z

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 d6bdd1a1-6a24-4dad-b7be-123f13f5c09c · outbound

This paper cites Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:57.025992Z

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 4f527707-ce98-47f7-9f26-9d30dff09837 · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.795455Z

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 57f6ad12-bcd2-428d-a55f-e1bb3dde946e · outbound

This paper cites PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.030529Z

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 e5c1383d-de45-46e6-9327-ea19121a83e1 · outbound

This paper cites Safepro: Evaluating the safety of professional-level ai agents.arXiv preprint arXiv:2601.06663, 2026.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Safepro: Evaluating the safety of professional-level ai agents.arXiv preprint arXiv:2601.06663, 2026

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:57.016964Z

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 27d9d08c-85b0-49c3-8ef9-23467c42abe9 · outbound

This paper cites Mcp-safetybench: A benchmark for safety evaluation of large language models with real-world mcp servers.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Mcp-safetybench: A benchmark for safety evaluation of large language models with real-world mcp servers

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.958592Z

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 dfac3783-4610-42ff-9440-cb100574a342 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-05-21T01:43:56.662569Z

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 287ada0c-ae60-400a-a549-643165fec13f · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-21T01:43:56.674346Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers