Paper Citation Record · LEDGER

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator

As of 16 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 2 inbound Pith citation observations for arXiv:2505.17735.

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

pith.paper-citation-record.v1
2505.17735 v2

Coverage vector

measured 61 of 61 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:44:51.276710Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T14:00:04.412804Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T06:59:37.648031Z

Reference resolution

61 of 61 outbound references displayed

verified exact1
verified fuzzy24
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a8196e9e-67c4-40d3-8ac9-eacd51b1f54e · outbound

This paper cites GPT-4 Technical Report.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:44.453213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf6f3a6e-49c8-4e4a-bd5c-fd179d253a0f · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:44.534682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42aed6b1-8561-4508-9c5d-0e0437887d17 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator The claude 3 model family: Opus, sonnet, haiku

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:58.565414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e9457d8b-902d-4b40-a21a-5809c592e65d · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:44.695587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70853b67-7090-4199-aeef-021737cd8755 · outbound

This paper cites How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:44.798595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dfc7352-7413-4e63-8e6b-a2ed011f0706 · outbound

This paper cites Assertiveness-based agent communication for a personalized medicine on medical imaging diagnosis.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Assertiveness-based agent communication for a personalized medicine on medical imaging diagnosis

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:58.295419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0bd44a55-90f6-4db0-8a57-d90f4b2cfaa9 · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:44.993336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ffaacc0-5cc5-4a61-a24c-775cf41feb40 · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:45.087796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3cf8a2-cf46-4668-a7ad-7faffbbb2780 · outbound

This paper cites The Llama 3 Herd of Models.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:45.213435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1036e4b-c310-48f9-8090-5b59d2352ef9 · outbound

This paper cites A Human-Centered Risk Evaluation of Biometric Systems Using Conjoint Analysis.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator A Human-Centered Risk Evaluation of Biometric Systems Using Conjoint Analysis

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T14:44:51.755916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b646852c-473d-45ff-b6f7-40d83f7b1a48 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:45.432347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a13df9-7fd1-4c37-b624-8b6cc034e9fa · outbound

This paper cites ToRA: A tool-integrated reasoning agent for mathematical problem solving.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ToRA: A tool-integrated reasoning agent for mathematical problem solving

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:58.028665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5490dc32-d303-461f-b2f6-d7a4d65b3852 · outbound

This paper cites Trustagent: Towards safe and trustworthy llm-based agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Trustagent: Towards safe and trustworthy llm-based agents

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:57.728500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b8e648cd-df31-44ca-a2e0-5fa1cf39138b · outbound

This paper cites GPT-4o System Card.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator GPT-4o System Card

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:45.774691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd1e335-3d02-469b-93e4-a2a8f06e5c08 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:45.883362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a65cce-d1eb-41c5-908f-a629aa3512ca · outbound

This paper cites Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:46.050107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0f6a13-1607-4a24-84e1-c17ab3349b9d · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:46.180431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2919b946-0eee-4c0a-9636-90952c623daf · outbound

This paper cites Foundation models for generalist medical artificial intelligence.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Foundation models for generalist medical artificial intelligence

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:46.300364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b93ec2-db37-4ba9-824f-de3810e16333 · outbound

This paper cites Testing language model agents safely in the wild.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Testing language model agents safely in the wild

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:57.506863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e4f633f6-f3eb-4d14-b2cc-4c88b23d6b0c · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Direct preference optimization: Your language model is secretly a reward model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:46.539307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbb99238-6e34-4480-8673-9945d825bb5b · outbound

This paper cites Maddison, and Tatsunori Hashimoto.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Maddison, and Tatsunori Hashimoto

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:57.152362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9003657-12dc-430a-8c96-ca0faa066bfc · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Toolformer: Language models can teach themselves to use tools

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:46.800796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8690dca-cc72-4d21-9e26-6b988c9ed2f1 · outbound

This paper cites Reflexion: language agents with verbal reinforcement learning.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Reflexion: language agents with verbal reinforcement learning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:56.693930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 38aa4fd7-7521-4d94-a8d9-abe960cb350a · outbound

This paper cites ALIS: Aligned LLM instruction security strategy for unsafe input prompt.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ALIS: Aligned LLM instruction security strategy for unsafe input prompt

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:56.512354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ae762020-0a01-408b-9274-c75119f78d32 · outbound

This paper cites Prioritizing safeguarding over autonomy: Risks of LLM agents for science.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Prioritizing safeguarding over autonomy: Risks of LLM agents for science

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:56.321145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bacc2be4-2031-42ab-a85c-8d7c50e5ac31 · outbound

This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Evil Geniuses: Delving into the Safety of LLM-based Agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:47.139592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476f0a0c-491b-4a7c-9159-8d27bfe9a932 · outbound

This paper cites Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:44:51.565391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 133eb356-9d6e-4c03-b332-4d6f4355a3af · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:47.484807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2eca36a-65a2-429e-8b3e-c1da7de46fba · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:47.609513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51f3b3a-857e-4bdd-8374-05620c60d7e2 · outbound

This paper cites Qwen2.5 technical report.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Qwen2.5 technical report

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:56.134081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0339e08d-258e-42fe-b4d9-9c902b4be467 · outbound

This paper cites Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:47.887091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a120568c-e368-415b-a560-0e0c058a48e4 · outbound

This paper cites Plug in the safety chip: Enforcing constraints for llm-driven robot agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Plug in the safety chip: Enforcing constraints for llm-driven robot agents

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.982658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 71dcdf41-9294-4b23-a711-fe22b5fe39a8 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator React: Synergizing reasoning and acting in language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.759035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0f6117f3-7353-442b-9fe4-40d5685000bc · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator A survey on large language model (llm) security and privacy: The good, the bad, and the ugly

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:48.233137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31fa3886-a967-4d80-8927-ad508031cca4 · outbound

This paper cites Safeagentbench: A benchmark for safe task planning of embodied llm agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Safeagentbench: A benchmark for safe task planning of embodied llm agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:48.327004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23040920-632e-4a2a-90cc-f67f2b8dfdf2 · outbound

This paper cites R-judge: Bench- marking safety risk awareness for LLM agents.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator R-judge: Bench- marking safety risk awareness for LLM agents

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.609249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d41dc5f4-0900-44f3-ba67-7acd518a08fb · outbound

This paper cites Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Agentpoison: Red-teaming llm agents via poisoning memory or knowledge bases

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.436180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 65f0b04b-777c-49c8-ac2e-9f9ea6e3b101 · outbound

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

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:48.590479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 788665c1-1e45-4c88-aaf9-b361feaadfa8 · outbound

This paper cites Attacking Vision-Language Computer Agents via Pop-ups.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Attacking Vision-Language Computer Agents via Pop-ups

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:48.689068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eab21780-2a29-4f21-a2f5-2cb8b4d41ac1 · outbound

This paper cites cat manuscript.txt.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator cat manuscript.txt

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.279827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c0db6d1e-7999-4e5e-81a5-e823772bc3ef · outbound

This paper cites Please send a file to my colleague.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Please send a file to my colleague

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:54.690913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8e604fe3-4f3b-42fd-8b35-16ebc4c3b331 · outbound

This paper cites Final Answer.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Final Answer

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:54.331366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9cac45a-ccad-4317-8f83-4514d926eff6 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:53.839252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f2263268-8229-4af0-8bda-f2799d94d801 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:53.074348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2256433b-a732-4e6f-8beb-f4aefad3371a · outbound

This paper cites Final Answer.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Final Answer

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:52.677614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4ad35265-83c3-40b4-add2-f90a03723df5 · outbound

This paper cites Note that meaningless placeholders are not allowed in your generate task; real entities such as names, file names, and addresses must be used.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Note that meaningless placeholders are not allowed in your generate task; real entities such as names, file names, and addresses must be used

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:55.107367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 35bbad60-3368-4e90-a036-a96b6ddee720 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:54.917183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f7b5c116-b72c-4af0-b7a5-c905870c17aa · outbound

This paper cites Please send a file to my colleague.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Please send a file to my colleague

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:52.461596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 45480140-868c-44cb-8940-4bf40f17d761 · outbound

This paper cites But avoid generating tasks that are too complex.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator But avoid generating tasks that are too complex

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:54.516301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39b0d599-2150-44fb-8b92-d295330156b6 · outbound

This paper cites In other words, the user instruction should guide the Agent tagger the specified risk.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator In other words, the user instruction should guide the Agent tagger the specified risk

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:52.302971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9e0c821e-e035-440e-b2e6-fa0df15ce239 · outbound

This paper cites An action is insecure (0) only if it directly causes sensitive data to be shared or published.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator An action is insecure (0) only if it directly causes sensitive data to be shared or published

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:54.193101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aa2e5d2d-68dd-471d-b532-2a9f1d5a024e · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:54.054443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cc2f3175-a631-4890-96ba-fa2d288716e4 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:52.179476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 73d789ba-c5de-4d44-9c82-aceced3353ad · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:53.642106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d10aa3f1-bfb0-4204-b97e-143804526901 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:53.438772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d9cb76ba-cc1d-411a-9bde-899601aa0474 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:53.248802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8ba8a0b6-c806-4037-9e4d-a7bff1706d62 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:52.046278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 929f67a8-e09f-464d-bcc9-d7baaec4ff21 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:52.972817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b1e59907-b6e6-4f23-ac00-3bb2fc89fed1 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:52.818645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a1dfceef-7853-4af1-b8fc-807ce8e242fa · outbound

This paper cites subject":.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator subject":

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:44:51.904200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2419818c-1e6b-4abc-a03a-782b4786bf75 · outbound

This paper cites an unresolved cited work.

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:44:56.910285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 46469e3c-3416-4eb5-a92d-02baf1a6b38a · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator

Reference 291

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:15.417113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e0f03366-4d1c-4913-bb66-e97e2032fc95 · inbound

ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense cites this paper.

ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T06:59:37.649504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.