Paper Citation Record · LEDGER

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.09885.

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

pith.paper-citation-record.v1
2608.09885 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:02:55.979647Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact1
verified fuzzy3
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8b47311e-61b9-4240-8360-4b04e597dfc7 · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.760898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59648144-b4be-4744-ae44-b9277fe4da27 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.777107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39a29c2-09f3-4466-a8f3-7f3dc3579363 · outbound

This paper cites Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.810833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b386a84e-feb3-401e-b7e6-ab9d42f2a79e · outbound

This paper cites EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.823305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e307ff1-8b92-45be-a335-77c6387d303f · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.838094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e703a554-590f-4871-9e70-36de1de5e10c · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.843781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1cf8647-ed82-4e2d-b2ab-08099c24e1c7 · outbound

This paper cites ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.848941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b102ac6-372c-4115-919f-d3a0fb43f1ae · outbound

This paper cites Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.855251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 544b7471-3ded-4e37-827c-761d3ffd9ef0 · outbound

This paper cites AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.861028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64be4ab5-3505-42aa-beb3-c152b7422030 · outbound

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

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.867097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ec64caf-d8cf-421c-b8e3-8cd77229cc6c · outbound

This paper cites Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:02:56.495472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 28f757f0-28c9-4a44-8035-1b018ec6cd7a · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.878836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f436c7c-442b-414d-a35e-23a55dcc8bc3 · outbound

This paper cites Accessed: 2026-07-26.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Accessed: 2026-07-26

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.884651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1249860-424c-4b7b-88b3-e0cb440aefb1 · outbound

This paper cites Accessed: 2026-07-26.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Accessed: 2026-07-26

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:02:56.863243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 22c603e3-ee8f-4550-88d1-4f9479adbddf · outbound

This paper cites Progent: Securing AI Agents with Privilege Control.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Progent: Securing AI Agents with Privilege Control

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.899019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e75b124-9ee9-4da2-a900-3571d20d6532 · outbound

This paper cites The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.905307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f29f00-2001-444b-a4eb-cd40fd6e5ded · outbound

This paper cites ABSTRAL: Automatic design of multi-agent systems through iterative refinement and topology optimization.arXiv preprint arXiv:2603.22791,.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents ABSTRAL: Automatic design of multi-agent systems through iterative refinement and topology optimization.arXiv preprint arXiv:2603.22791,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.910843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ebbe66a-ac36-4289-ab7e-84375012b328 · outbound

This paper cites SkillOpt: Executive Strategy for Self-Evolving Agent Skills.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents SkillOpt: Executive Strategy for Self-Evolving Agent Skills

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.917946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36977ecf-757f-4ff2-833c-282a924a43cd · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.936859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2969d2-cf4e-44be-9acd-9fedf27c5c64 · outbound

This paper cites R-Judge: Benchmarking safety risk awareness for LLM agents.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents R-Judge: Benchmarking safety risk awareness for LLM agents

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:02:56.836258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cb546907-9ed8-4430-a3fd-2df7347e8166 · outbound

This paper cites an unresolved cited work.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:02:56.816706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7eef1df5-5708-423a-8ac9-7b3b48e5d629 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.960250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc926af3-7cca-48b9-8cbd-ea7b61c90c9e · outbound

This paper cites Self-Harness: Harnesses That Improve Themselves.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Self-Harness: Harnesses That Improve Themselves

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.966211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f211ff1c-57d9-4883-b775-10c8a52fb53c · outbound

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

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.973774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 478cb12e-20c3-4b5d-b3a8-2fa1705c798b · outbound

This paper cites ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.979647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea3bf96-73ea-4260-a878-3545167f9d19 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.784125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f63d2f-133a-4c2a-aedc-a302ffd42ca7 · outbound

This paper cites The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.793564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edbd400d-218b-4fe3-8f05-4bead4d81db1 · outbound

This paper cites 10 Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, and Yuning Mao.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents 10 Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, and Yuning Mao

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:02:56.883564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 26eb5d9d-7740-4ba0-8bf1-e85c74f8eda8 · outbound

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

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.770978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d37f90ff-5756-43b2-83a3-478c45d07777 · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-11T05:02:55.803576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.