Paper Citation Record · LEDGER

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

As of 6 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 2 inbound Pith citation observations for arXiv:2605.05704.

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

pith.paper-citation-record.v1
2605.05704 v3

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T14:48:00.709259Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-13T17:08:58.831798Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T13:46:59.950882Z

Reference resolution

10 of 10 outbound references displayed

verified exact0
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9d5458ca-4345-412a-9fc3-adbb5306181a · outbound

This paper cites Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.069536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd944e26-d04e-4724-9614-a216e644c277 · outbound

This paper cites an unresolved cited work.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.305580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac574b9-1d97-424e-8080-e65a9c78a7bb · outbound

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

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 4695080c-386e-4d99-b7fa-04a703fd7e7b · outbound

This paper cites R., and Cao, Y.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety R., and Cao, Y

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.495126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59ae28aa-5284-4602-bc98-139c6393f555 · outbound

This paper cites F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y ., Fried, D., et al.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y ., Fried, D., et al

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.709259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba3658c-cd96-42a3-bf95-7a1ba4007cd2 · outbound

This paper cites Drat- tack: Prompt decomposition and reconstruction makes powerful llms jailbreakers.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety Drat- tack: Prompt decomposition and reconstruction makes powerful llms jailbreakers

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.014118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b07044e-8b57-4694-b1ab-6650bc8294ad · outbound

This paper cites AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.583099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52e98c9a-6352-4f1c-ad54-5151021b1651 · outbound

This paper cites Your agent may misevolve: Emergent risks in self-evolving llm agents.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety Your agent may misevolve: Emergent risks in self-evolving llm agents

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.243373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f426a13d-9336-43e0-9ed9-a985e681b0d8 · outbound

This paper cites Andriushchenko, M., Croce, F., and Flammarion, N.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety Andriushchenko, M., Croce, F., and Flammarion, N

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T14:47:59.934688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2189d0d-594d-412e-9dcc-13032ae19b75 · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T14:48:00.157561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b5409124-aaee-45f8-972b-5a7fa56e2e81 · inbound

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses cites this paper.

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Reference 240

Resolution: unresolved; no resolver link, observed 2026-07-13T17:08:58.831798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b5dd8f-5d29-4275-8b72-fa95e88725ce · inbound

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense cites this paper.

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T13:46:59.952250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.