Paper Citation Record · LEDGER

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2607.18063.

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

pith.paper-citation-record.v1
2607.18063 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T16:19:08.659588Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

13 of 13 outbound references displayed

verified exact0
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cb9d54ac-a36d-49d8-8a77-d270fe776526 · outbound

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

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.591855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10f70f7c-61ec-4297-bb8c-aa8255be8e44 · outbound

This paper cites an unresolved cited work.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.632076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d47b433a-ecdd-4c60-bf5f-c86b2e713985 · outbound

This paper cites Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.637388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb1f7e20-d6c8-44c1-b2c6-e26358957c51 · outbound

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

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.642230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87315c15-adac-4ece-8b2c-ae5182aef1ee · outbound

This paper cites static scanner false positive.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security static scanner false positive

Reference 11

Resolution: malformed identifier; no resolver link, observed 2026-08-01T16:19:08.646941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88f25e9e-539c-4864-9000-f8e8b018bb8f · outbound

This paper cites metadata.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security metadata

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.659588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2543fac7-c219-41b2-8216-1b93274a14d9 · outbound

This paper cites discrimination.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security discrimination

Reference 46

Resolution: malformed identifier; no resolver link, observed 2026-08-01T16:19:08.653322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52be3610-9d22-4093-b472-d455bb546b5d · outbound

This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Reference 1939

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.626130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a980366c-883e-4df2-b65b-529546b13abb · outbound

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

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 2000

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.620825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e85ae6c-d35b-43d4-a19d-aa88b69d0520 · outbound

This paper cites Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Pappas, Florian Tramèr, Hamed Hassani, and Eric Wong

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.609960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20af0eb7-595f-4044-ac48-05c1df91ff6a · outbound

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

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.615174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4128cf2e-4331-435a-ac9f-e32c8e1046d9 · outbound

This paper cites Breaking agent backbones: Evaluating the security of backbone LLMs in AI agents.arXiv preprint arXiv:2510.22620,.

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Breaking agent backbones: Evaluating the security of backbone LLMs in AI agents.arXiv preprint arXiv:2510.22620,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.598377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b301f0e-cb13-4c73-b675-e3ed922cd45a · outbound

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

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T16:19:08.603833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.