Paper Citation Record · LEDGER

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

As of 14 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 1 inbound Pith citation observation for arXiv:2606.00914.

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

pith.paper-citation-record.v1
2606.00914 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T18:18:52.472535Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T11:44:10.317641Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

14 of 14 outbound references displayed

verified exact3
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8d629cd0-2247-4fff-829a-8d8fe0549658 · outbound

This paper cites 2022 , eprint =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2022 , eprint =

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc729e86-077c-4054-a76a-e19df4ddd24f · outbound

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

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-28T20:52:38.011812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bdbce250-54f8-40ab-9a06-8cf9cb9b4078 · outbound

This paper cites 33rd USENIX Security Symposium (USENIX Security 24) , year =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 33rd USENIX Security Symposium (USENIX Security 24) , year =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cd732be-6fff-4da3-91f6-17760dadc02b · outbound

This paper cites 2023 , eprint =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2023 , eprint =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46fa93b4-522d-4d55-821f-8105162fdbdd · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T20:52:38.003084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bb7afc38-87a7-46d3-b7d5-65d7549c6b6e · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track , year =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track , year =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30f6e16e-bf09-4286-a74a-262e9ccbb7bb · outbound

This paper cites 2023 , eprint =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2023 , eprint =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6dc2381-46e3-4b75-bbfb-1086654cdf94 · outbound

This paper cites 2023 , eprint =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2023 , eprint =

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c859da42-bdec-40eb-94c5-ed540034df2e · outbound

This paper cites 2023 , howpublished =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2023 , howpublished =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8e1cbd6-f9e1-4775-88ba-8f008fa426d8 · outbound

This paper cites an unresolved cited work.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd4d23c-50f6-4377-af19-f5d52ac07333 · outbound

This paper cites an unresolved cited work.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15de81bb-a6e6-4753-a568-5872b40279d4 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-28T20:52:37.999657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bd66ba43-87fe-404e-baa2-0f956d06bc03 · outbound

This paper cites 2025 , eprint =.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults 2025 , eprint =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T18:18:52.472535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b2861b-6791-41e5-a7f2-f7cb2cfe1322 · outbound

This paper cites Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents.

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-28T20:52:38.007689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation ad3c1156-e091-4a59-b511-3ae265753e4e · inbound

PhantomFill: When the Form Demands an Answer, Language Models Invent One cites this paper.

PhantomFill: When the Form Demands an Answer, Language Models Invent One Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T11:44:10.317641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.