Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-21T01:57:50.346715Z
Paper Citation Record · LEDGER
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
As of 11 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 53 inbound Pith citation observations for arXiv:2406.09187.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-11T10:24:27.034983Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-04T20:40:07.847472Z
Reference resolution
15 of 15 outbound references displayed
- verified exact3
- verified fuzzy6
- unresolved2
- parse uncertain0
- malformed identifier1
- metadata mismatch3
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation fdb07572-eb00-4933-8610-9c685f320fcc · outbound
This paper cites Conversational Health Agents: A Personalized LLM-Powered Agent Framework.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Conversational Health Agents: A Personalized LLM-Powered Agent Framework
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T01:57:50.376119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 4c608718-f1dd-437b-b55a-d944c60e4aa2 · outbound
This paper cites Mind2Web: Towards a Generalist Agent for the Web.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Mind2Web: Towards a Generalist Agent for the Web
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T01:57:50.385394Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 577c9d34-c064-4449-891f-c64af1bd86da · outbound
This paper cites Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-21T01:57:50.394569Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c026b283-8570-40aa-8c8d-fffc6ec62321 · outbound
This paper cites EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T01:57:50.402917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation e16b437c-4192-4c88-b2e5-fb0aa38b74e9 · outbound
This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning The Rise and Potential of Large Language Model Based Agents: A Survey
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-21T01:57:50.410157Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 230cdb62-c650-43da-9576-28dbaa72bcca · outbound
This paper cites PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning PsychoGAT: A Novel Psychological Measurement Paradigm through Interactive Fiction Games with LLM Agents
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T01:57:50.416508Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3e85aeaf-65c1-4c43-be63-cb75e20ca628 · outbound
This paper cites model guarding agent.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning model guarding agent
Reference 7
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-21T01:57:50.421120Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f4d75fb1-cc7f-4942-8b30-34e6c0b3b0b4 · outbound
This paper cites eye” and “eyes.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning eye” and “eyes
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.425195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 4c0ec47b-efeb-4484-9f5c-79483df76bac · outbound
This paper cites an unresolved cited work.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T01:57:50.429236Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bf6ca643-5cf9-4574-a0f1-f88517535181 · outbound
This paper cites an unresolved cited work.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-21T01:57:50.433187Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 664a1a79-e98e-4d2b-a57f-f7b89bf0995b · outbound
This paper cites model guarding agents.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning model guarding agents
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.437616Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3594de7d-bb89-4464-87d4-9e8c365b292f · outbound
This paper cites An important future research is to have the agent (or an auxiliary agent) create the required tools.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning An important future research is to have the agent (or an auxiliary agent) create the required tools
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.441997Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation c311a214-a2cc-4c67-ba5b-747e3240f890 · outbound
This paper cites Currently, the reasoning is based on a simple chain of thought without any validation of the reasoning steps.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning Currently, the reasoning is based on a simple chain of thought without any validation of the reasoning steps
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.446153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3d57ca57-fb26-460a-8588-615a986c1e0f · outbound
This paper cites faculty members from colleges A and B, and graduate assistants from college C and department a of college D cannot access database α.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning faculty members from colleges A and B, and graduate assistants from college C and department a of college D cannot access database α
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.450304Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 9502ab1b-1784-4db8-b66f-de721f1970e8 · outbound
This paper cites pseudo access control.
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning pseudo access control
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-21T01:57:50.453952Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Pith citing papers
Observation cc2220d0-1558-4024-afb5-2de29e82a5bf · inbound
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents cites this paper.
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 29
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 55a100af-990e-4bbc-b180-2afb7374885a · inbound
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents cites this paper.
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-11T10:24:27.034983Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2987e34e-e430-496a-abce-b2351b0a6969 · inbound
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents cites this paper.
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 46
- Resolution
- metadata mismatch
- 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 2026-08-11T06:34:44.6726+00:00.
Observation b2eca36a-65a2-429e-8b3e-c1da7de46fba · inbound
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator cites this paper.
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 d402eb36-565c-4176-a53a-60161258d2dc · inbound
WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.
WebGuard: Building a Generalizable Guardrail for Web Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T16:12:50.914742Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 982bb04e-5d8c-42b8-8605-30e4abd93433 · inbound
Agentic Web: Weaving the Next Web with AI Agents cites this paper.
Agentic Web: Weaving the Next Web with AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 234
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T13:05:40.427092Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c9e9d02-8ab2-460c-85d8-60909dd53159 · inbound
Reliable Weak-to-Strong Monitoring of LLM Agents cites this paper.
Reliable Weak-to-Strong Monitoring of LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T15:53:56.054241Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d4b8ffe-5a44-4cf2-bb60-9cf8c4b5a1d5 · inbound
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 134
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:39:06.979333Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7325c079-916c-454f-a7b6-6a854f09389a · inbound
Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities cites this paper.
Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 161
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 10e7f1da-024b-4a40-b3e2-c724420648b1 · inbound
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents cites this paper.
AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T21:44:12.441954Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cdd22b8-ba24-4160-be02-e8a5d7f8145a · inbound
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails cites this paper.
From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T20:44:21.969824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 9d3c07a2-712b-4fc3-8f88-fdac9a03ec61 · inbound
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 205
- 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 2026-08-11T06:34:44.6726+00:00.
Observation be2008a9-e718-4f92-ac24-039d8f74acc3 · inbound
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 77
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T07:06:38.131932Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef8c0c5c-0f55-4d82-8fcb-926b4e3fbcd8 · inbound
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents cites this paper.
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 27
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 58629994-388f-4cab-a5f5-ef5e95ef7f72 · inbound
Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection cites this paper.
Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T15:20:17.382272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bc93ce2a-9fab-44b0-a5ee-d81b2e4f9102 · inbound
Formal Policy Enforcement for Real-World Agentic Systems cites this paper.
Formal Policy Enforcement for Real-World Agentic Systems GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 65
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 896badfb-2c40-45a2-95be-a1f897b3a72d · inbound
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning cites this paper.
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T20:28:46.962122Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dee02f47-55b4-4562-8ce4-e05fed7e6574 · inbound
Tracking Capabilities for Safer Agents cites this paper.
Tracking Capabilities for Safer Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 80
- 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 2026-08-11T06:34:44.6726+00:00.
Observation e8980770-b9b3-4301-a5bd-5aac0f26c68e · inbound
Governance-Aware Agent Telemetry for Closed-Loop Enforcement in Multi-Agent AI Systems cites this paper.
Governance-Aware Agent Telemetry for Closed-Loop Enforcement in Multi-Agent AI Systems GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 16
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 907a9e0f-fdd3-4d88-b646-f2ff9b469faf · inbound
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution cites this paper.
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 46
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 1225e056-2c28-4c3b-94f4-114421dc72a0 · inbound
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution cites this paper.
Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 46
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T10:41:25.229406Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f7db162e-ff58-48a9-b08a-ad8e3ca757ca · inbound
PolicyBank: Evolving Policy Understanding for LLM Agents cites this paper.
PolicyBank: Evolving Policy Understanding for LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 1
- Resolution
- metadata mismatch
- 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 2026-08-11T06:34:44.6726+00:00.
Observation c2924d25-02fb-4ed4-8e9d-71a172aa1ada · inbound
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents cites this paper.
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 72
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 7ae49584-94cf-46a9-81f7-3ca52797290f · inbound
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents cites this paper.
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 49
- 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 2026-08-11T06:34:44.6726+00:00.
Observation de61da63-6192-4f02-b8c5-a03cd9d6a311 · inbound
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems cites this paper.
Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 57
- 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 2026-08-11T06:34:44.6726+00:00.
Observation fe9dc1a5-1733-4966-ac78-cd1a47ed75f3 · inbound
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety cites this paper.
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 8
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 85447b4e-0957-4656-87e6-942f185980e8 · inbound
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety cites this paper.
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-25T06:20:24.246455Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation bac574b9-1d97-424e-8080-e65a9c78a7bb · inbound
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety cites this paper.
SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T14:48:00.400543Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1cbc304b-9163-474b-a2df-e80ebc070e7e · inbound
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium cites this paper.
EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 81
- 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 2026-08-11T06:34:44.6726+00:00.
Observation a7389fb1-7325-4efd-bf46-f2b1ca899824 · inbound
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck cites this paper.
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 29
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 711d6913-6b3d-45eb-b026-c57ef23d2871 · inbound
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections cites this paper.
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 71
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:45:49.612948Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation f173b4f1-8002-403e-810a-5e7ea4ea94c8 · inbound
AgentWall: A Runtime Safety Layer for Local AI Agents cites this paper.
AgentWall: A Runtime Safety Layer for Local AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T10:09:59.451999Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 3dc32d50-682f-4799-860e-6f84d6ceb9db · inbound
Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.
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 2026-08-11T06:34:44.6726+00:00.
Observation f4f0b56c-3791-4083-a05d-24438358e9b7 · inbound
ADR: An Agentic Detection System for Enterprise Agentic AI Security cites this paper.
ADR: An Agentic Detection System for Enterprise Agentic AI Security GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 31
- Resolution
- metadata mismatch
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 54e66a4f-33f3-4e18-9cae-1a1fa564e98d · inbound
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains cites this paper.
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 52
- 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 2026-08-11T06:34:44.6726+00:00.
Observation 4b8e6caf-b85b-4b40-ba3a-a21b0093e436 · inbound
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents cites this paper.
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 34
- 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 2026-08-11T06:34:44.6726+00:00.
Observation c5ff9585-27ad-41ab-a9ec-3c6a20128809 · inbound
No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents cites this paper.
No Certificate, No Execution: Certified Traces as a Foundation for Trustworthy AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T12:34:38.976711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 75a850b7-1748-4a02-959f-0f9fbc04b9b0 · inbound
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents cites this paper.
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T18:53:51.634817Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation fecdc5fa-9632-43eb-93c2-b8b6adb01fe8 · inbound
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling cites this paper.
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T18:13:48.605358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0e9eda3f-7780-4ebb-934d-85c9b74161bd · inbound
BraveGuard: From Open-World Threats to Safer Computer-Use Agents cites this paper.
BraveGuard: From Open-World Threats to Safer Computer-Use Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T21:26:14.216881Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 6ee901b8-abb4-4f7c-b538-59f5473effc1 · inbound
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction cites this paper.
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 25
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T22:46:19.946241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation ea2de178-aa8a-4750-9127-f76320fd1ab1 · inbound
Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda cites this paper.
Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T14:08:21.999118Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 8f12bbbe-a0a7-44bf-b03c-7d22e21ca3d0 · inbound
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents cites this paper.
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T08:59:42.365779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation facc9d23-84b4-4d42-b96a-6f0c62bdeb06 · inbound
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents cites this paper.
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 21
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T10:44:36.381076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 0dc307de-b040-4fbf-92fa-21daa178cb27 · inbound
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents cites this paper.
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 147
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T20:40:07.849014Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation 7df9b22c-32a4-4923-9035-5d5f6b244fd0 · inbound
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents cites this paper.
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 121
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T14:09:53.040476Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.
Observation d20f98ca-a415-40ce-93d9-2e11d463a69f · inbound
DualView: Preventing Indirect Prompt Injection in Personal AI Agents cites this paper.
DualView: Preventing Indirect Prompt Injection in Personal AI Agents GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-07-11T23:43:28.649948Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3626da50-f91e-45aa-bcb8-8060c5a162e6 · inbound
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy cites this paper.
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 272
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T06:30:16.612345Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34e42c67-f001-493e-ac1f-fbb0e2ed3ff5 · inbound
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing cites this paper.
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T04:49:09.194533Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 913dc9ff-7860-4fa5-a1dc-bc602e374295 · inbound
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? cites this paper.
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T16:32:04.064947Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9cf2bff0-0bdd-4275-aaf3-b08dd6fb9c2f · inbound
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety cites this paper.
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T11:24:49.070762Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f324083-61a9-49fd-ad26-d21ce208bb9a · inbound
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems cites this paper.
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T03:01:03.860989Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 627c5c47-e35d-4976-9fc7-88b4552e69ba · inbound
ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution cites this paper.
ChainClaw: A Layered Agent Framework for Reliable On-Chain Execution GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T23:31:04.389624Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.