Paper Citation Record · LEDGER

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

As of 20 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 1 inbound Pith citation observation for arXiv:2606.26793.

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

pith.paper-citation-record.v1
2606.26793 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T04:32:29.379691Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T15:12:55.506678Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact2
verified fuzzy0
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c16ccb44-f9df-42be-b905-08497aac2013 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Retrieval-augmented generation for knowledge-intensive NLP tasks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29286179-ebf3-429d-ae0c-2ea964574339 · outbound

This paper cites Dense passage retrieval for open-domain question answer- ing,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Dense passage retrieval for open-domain question answer- ing,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0f63338-f3c7-44b0-9b85-7c1473db132e · outbound

This paper cites Learning transferable visual models from natural language supervi- sion,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Learning transferable visual models from natural language supervi- sion,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce29bc01-81a1-4e4b-94fc-c8dac90e7abc · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG ReAct: Synergizing reasoning and acting in language models,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2657412a-be1d-426e-8841-89c0fc289182 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world LLM- integrated applications with indirect prompt injection,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Not what you’ve signed up for: Compromising real-world LLM- integrated applications with indirect prompt injection,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f529d8cb-5217-4432-9342-88af4662bbe2 · outbound

This paper cites PoisonedRAG: Knowledge corruption attacks to retrieval-augmented generation of large language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG PoisonedRAG: Knowledge corruption attacks to retrieval-augmented generation of large language models,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd547d1-a12e-4a53-97fb-a422cf32a289 · outbound

This paper cites TrojanRAG: Retrieval-augmented generation can be backdoor driver in large language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG TrojanRAG: Retrieval-augmented generation can be backdoor driver in large language models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b6d1d3-207a-45c5-a56b-eda9b55a4b53 · outbound

This paper cites Injecagent: Benchmark- ing indirect prompt injections in tool-integrated large language model agents,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Injecagent: Benchmark- ing indirect prompt injections in tool-integrated large language model agents,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a02f1bc-d2d8-49f8-ba1f-32316dd138b8 · outbound

This paper cites Art-safebench,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Art-safebench,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cffd67a-d594-4b8d-9c73-31e8789a3b25 · outbound

This paper cites HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG HarmBench: A standardized evaluation framework for automated red teaming and robust refusal,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1eccaae-f5a8-443c-b3f7-bdb5f01e6a5b · outbound

This paper cites Figstep: Jailbreaking large vision-language models via typographic visual prompts,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Figstep: Jailbreaking large vision-language models via typographic visual prompts,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 060eeadf-027b-489b-9a6a-e4467f5e7acd · outbound

This paper cites Jailbreakbench: An open robustness benchmark for jailbreaking large language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Jailbreakbench: An open robustness benchmark for jailbreaking large language models,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56289fbf-9cb5-47db-a2c2-9e3a8ec6a93d · outbound

This paper cites CODE: A contradiction-based deliberation extension framework for overthinking attacks on retrieval- augmented generation,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG CODE: A contradiction-based deliberation extension framework for overthinking attacks on retrieval- augmented generation,

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:09:52.862563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 92321b46-afd7-4c40-9cc4-7b5044719266 · outbound

This paper cites Advancing deep metric learning with adversarial robustness,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Advancing deep metric learning with adversarial robustness,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81d729ea-c605-42c5-a843-a45bbd55b805 · outbound

This paper cites Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, and Amir Houmansadr.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, and Amir Houmansadr

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T14:09:52.866166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9d6ddf3f-e6f5-4eae-834e-2336ab453bcf · outbound

This paper cites CyberRAG: An agentic RAG cyber attack classification and reporting tool,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG CyberRAG: An agentic RAG cyber attack classification and reporting tool,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3223a858-0ded-4c50-8980-ff8467255fce · outbound

This paper cites DAMON: A dialogue-aware MCTS framework for jailbreaking large language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG DAMON: A dialogue-aware MCTS framework for jailbreaking large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1ca8e7-7d45-4d44-9285-d6ad7aae14d2 · outbound

This paper cites MUSE: MCTS-driven red teaming framework for enhanced multi-turn dialogue safety in large language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG MUSE: MCTS-driven red teaming framework for enhanced multi-turn dialogue safety in large language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219b7538-9f8b-40c2-8911-347f044699e2 · outbound

This paper cites arXiv preprint arXiv:2504.15047 (2025).

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG arXiv preprint arXiv:2504.15047 (2025)

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T14:09:52.863057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bce409d2-a5e9-4201-8b50-704a024a43c1 · outbound

This paper cites Digital red queen: Adversarial program evolution in core war with llms.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Digital red queen: Adversarial program evolution in core war with llms

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:09:52.869271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 49391683-08f0-490e-bd76-8a1168256748 · outbound

This paper cites Jailbreaking black box large language models in twenty queries,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Jailbreaking black box large language models in twenty queries,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d43d147-87c6-4853-9c7d-6cdbb6d96add · outbound

This paper cites Tree of attacks: Jailbreaking black-box LLMs automatically,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Tree of attacks: Jailbreaking black-box LLMs automatically,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335741e0-24ed-43b4-977d-ececdde12c6d · outbound

This paper cites Universal and transferable adversarial attacks on aligned language models,.

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Universal and transferable adversarial attacks on aligned language models,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-26T04:32:29.379691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 320e0c74-05a8-4db0-b957-c6a270dea960 · inbound

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents cites this paper.

Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T15:12:55.506678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.