Paper Citation Record · LEDGER

Interpretable Risk Mitigation in LLM Agent Systems

As of 23 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 3 inbound Pith citation observations for arXiv:2505.10670.

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

pith.paper-citation-record.v1
2505.10670 v1

Coverage vector

measured 77 of 77 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:11:02.149478Z

measured 80 of 80 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:51:56.450815Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-17T00:31:24.634056Z

Reference resolution

77 of 77 outbound references displayed

verified exact2
verified fuzzy24
unresolved49
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c43eafac-f59d-4479-8e8e-f89c0279a822 · outbound

This paper cites Artificial intelligence and the future of work: Evidence from OECD countries.

Interpretable Risk Mitigation in LLM Agent Systems Artificial intelligence and the future of work: Evidence from OECD countries

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.643143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf3d3a32-c723-4ab7-a21a-243b73e9489b · outbound

This paper cites Dai, Chelsea Finn, Justin Fu, Kanishka Gopalakrishnan, et al.

Interpretable Risk Mitigation in LLM Agent Systems Dai, Chelsea Finn, Justin Fu, Kanishka Gopalakrishnan, et al

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.627827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3801ed77-8037-4a96-b87d-1b592e49f25f · outbound

This paper cites Mistral 7b: Open foundation models, 2023.

Interpretable Risk Mitigation in LLM Agent Systems Mistral 7b: Open foundation models, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.612474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 54ed5ba8-5bf9-4e48-a28b-7b79fb7685e8 · outbound

This paper cites Playing repeated games with Large Language Models.

Interpretable Risk Mitigation in LLM Agent Systems Playing repeated games with Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.796811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7eff9b-d167-419d-ae41-da6ca8c46fe7 · outbound

This paper cites Concrete Problems in AI Safety.

Interpretable Risk Mitigation in LLM Agent Systems Concrete Problems in AI Safety

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.802560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16702f8c-2cb7-4d44-a2c2-8387f4b0ae83 · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.597680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 94b9346b-084f-4af5-a678-a12f9bd12757 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Interpretable Risk Mitigation in LLM Agent Systems Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.813065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e6eafe6-a930-4240-a93e-aaa30f5aa5d6 · outbound

This paper cites Emergent tool use from multi-agent autocurricula.

Interpretable Risk Mitigation in LLM Agent Systems Emergent tool use from multi-agent autocurricula

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.580794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 351ad7f1-6ab1-403d-b7ff-ef072b69c117 · outbound

This paper cites Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell.

Interpretable Risk Mitigation in LLM Agent Systems Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.562891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8a106779-c66d-48c7-8c48-b0f78d8abf43 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Interpretable Risk Mitigation in LLM Agent Systems On the Opportunities and Risks of Foundation Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.826932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a7adc57-b623-480d-be0c-b1dd7e69a6ee · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.544642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a338b78c-533d-4e4b-9b30-639f80356236 · outbound

This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.

Interpretable Risk Mitigation in LLM Agent Systems RT-1: Robotics Transformer for Real-World Control at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.836214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d22cc2-e43f-4ec2-aff9-61a6d878a1a6 · outbound

This paper cites Playing games with gpt: What can we learn about a large language model from canonical strategic games? SSRN Electronic Journal, 2023.

Interpretable Risk Mitigation in LLM Agent Systems Playing games with gpt: What can we learn about a large language model from canonical strategic games? SSRN Electronic Journal, 2023

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.526152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fa8b734c-b330-4c95-85f8-426bab50f0df · outbound

This paper cites Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D.

Interpretable Risk Mitigation in LLM Agent Systems Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.508895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b60e728a-df0f-4060-9aeb-3d455d436d74 · outbound

This paper cites What can machine learning do? workforce implications.

Interpretable Risk Mitigation in LLM Agent Systems What can machine learning do? workforce implications

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.491497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e55a86e7-747f-4031-8209-67c0bab512ab · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Interpretable Risk Mitigation in LLM Agent Systems Evaluating Large Language Models Trained on Code

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.853101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08b4f22d-3581-40e0-aa27-dd14aaa9041a · outbound

This paper cites Instigating cooperation among llm agents using adaptive information modulation.

Interpretable Risk Mitigation in LLM Agent Systems Instigating cooperation among llm agents using adaptive information modulation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.857296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72433d46-a595-481b-a5ef-2f80a6405e69 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Interpretable Risk Mitigation in LLM Agent Systems Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.870732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eadd38c1-fbcd-4b04-a105-2ea6f1e6a5e6 · outbound

This paper cites Reinforcement learning in a prisoner’s dilemma.

Interpretable Risk Mitigation in LLM Agent Systems Reinforcement learning in a prisoner’s dilemma

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.458432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 24f6a202-78a8-481d-8db8-1c4b79df229d · outbound

This paper cites Toy Models of Superposition.

Interpretable Risk Mitigation in LLM Agent Systems Toy Models of Superposition

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.880133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3da5c266-6d9b-45d6-8d90-16eafac12480 · outbound

This paper cites PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples.

Interpretable Risk Mitigation in LLM Agent Systems PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T21:11:02.834041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9a93bcfe-f4cc-4a52-9e56-a716c5208000 · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

Interpretable Risk Mitigation in LLM Agent Systems Not All Language Model Features Are One-Dimensionally Linear

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.891128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ab46e3-96c8-4341-b15b-4ef484f62fc1 · outbound

This paper cites Some experimental games.

Interpretable Risk Mitigation in LLM Agent Systems Some experimental games

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.442507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f9da16f4-a983-41b4-b6d2-cccdb6ba0154 · outbound

This paper cites Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?.

Interpretable Risk Mitigation in LLM Agent Systems Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.900891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88637004-c8d5-4677-890d-d755e3357d38 · outbound

This paper cites Artificial intelligence, values, and alignment.

Interpretable Risk Mitigation in LLM Agent Systems Artificial intelligence, values, and alignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.906112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb688a1f-ae7d-4316-9fcd-3ddffe2c900b · outbound

This paper cites The Llama 3 Herd of Models.

Interpretable Risk Mitigation in LLM Agent Systems The Llama 3 Herd of Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.910539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aea34d7-c236-4ba2-b05c-5266d05cbe3a · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Interpretable Risk Mitigation in LLM Agent Systems Measuring Massive Multitask Language Understanding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.915548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daa69867-514e-4500-ac68-9b455cec0cf3 · outbound

This paper cites Measuring mathematical problem solving with the math dataset,.

Interpretable Risk Mitigation in LLM Agent Systems Measuring mathematical problem solving with the math dataset,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.920013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc257f3-639b-4bd7-b693-d99e2d88ec53 · outbound

This paper cites Cogagent: A visual language model for gui agents.

Interpretable Risk Mitigation in LLM Agent Systems Cogagent: A visual language model for gui agents

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.416984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f465e08f-8581-42e6-b51b-25e319bc463c · outbound

This paper cites Non-linear inference time intervention: Improving llm truthfulness.

Interpretable Risk Mitigation in LLM Agent Systems Non-linear inference time intervention: Improving llm truthfulness

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.400826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 79c959d9-a3b3-4327-86ed-96acb55e005b · outbound

This paper cites Towards Reasoning in Large Language Models: A Survey.

Interpretable Risk Mitigation in LLM Agent Systems Towards Reasoning in Large Language Models: A Survey

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.939936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8bf0ff6-e450-4f1c-b07c-950516506ed9 · outbound

This paper cites Large language models for uavs: Current state and pathways to the future.

Interpretable Risk Mitigation in LLM Agent Systems Large language models for uavs: Current state and pathways to the future

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.384589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a7a39f6f-26fb-4c28-b196-bc2a237200ff · outbound

This paper cites Mixtral of Experts.

Interpretable Risk Mitigation in LLM Agent Systems Mixtral of Experts

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.949339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 017ef2a9-5520-4eb9-bdc4-f92641554c31 · outbound

This paper cites llama-3-8b-it-res (revision 53425c3), 2024.

Interpretable Risk Mitigation in LLM Agent Systems llama-3-8b-it-res (revision 53425c3), 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.367736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 91339d58-f620-44d4-8eb7-b59703b0d07a · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.350181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1a302ee4-fd9f-46ae-8fab-c55bc4736872 · outbound

This paper cites Martin, Hans-Theo Normann, and T.

Interpretable Risk Mitigation in LLM Agent Systems Martin, Hans-Theo Normann, and T

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.333745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 71a8d99b-1365-4a5b-ac7b-cce9c7fceaf8 · outbound

This paper cites Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al.

Interpretable Risk Mitigation in LLM Agent Systems Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.318008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 53ae654e-f604-43fa-bec1-7e4bbe48d9bf · outbound

This paper cites Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.

Interpretable Risk Mitigation in LLM Agent Systems Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.971070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation accf6756-7ccc-46fa-8ac0-5a95cac9c7e1 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Interpretable Risk Mitigation in LLM Agent Systems Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.975880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1e40780-c265-4c8d-b588-0f4db9b277d5 · outbound

This paper cites The mythos of model interpretability.

Interpretable Risk Mitigation in LLM Agent Systems The mythos of model interpretability

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.302405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4fc9c058-9b7f-4030-b591-6b05a8f26e5f · outbound

This paper cites Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.

Interpretable Risk Mitigation in LLM Agent Systems Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.989753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cdffd23-9790-4415-81f6-49a0963613c8 · outbound

This paper cites Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models.

Interpretable Risk Mitigation in LLM Agent Systems Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.994175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c86296d2-ed87-49d3-b9f2-78d6f82f7afa · outbound

This paper cites Linguistic regularities in continuous space word representations.

Interpretable Risk Mitigation in LLM Agent Systems Linguistic regularities in continuous space word representations

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.259770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a59a7951-c2e9-43c9-a557-199380bc4da6 · outbound

This paper cites Large Language Models: A Survey.

Interpretable Risk Mitigation in LLM Agent Systems Large Language Models: A Survey

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.008126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fae7cda6-218c-4394-8746-aa9f8ca079ab · outbound

This paper cites A strategy of win-stay, lose-shift that outperforms tit-for-tat in the prisoner’s dilemma game.

Interpretable Risk Mitigation in LLM Agent Systems A strategy of win-stay, lose-shift that outperforms tit-for-tat in the prisoner’s dilemma game

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.013053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4826b429-d15b-417a-b168-ff52c95b5cbc · outbound

This paper cites Training language models to follow instructions with human feedback.

Interpretable Risk Mitigation in LLM Agent Systems Training language models to follow instructions with human feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.018166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 014ab367-984a-479d-83c0-103ef33837a1 · outbound

This paper cites Cooperation: A systematic review of how to enable agent to circumvent the prisoner’s dilemma.

Interpretable Risk Mitigation in LLM Agent Systems Cooperation: A systematic review of how to enable agent to circumvent the prisoner’s dilemma

Reference 48

Resolution: verified exact; raw_fallback, observed 2026-08-15T21:11:02.613607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a05f4db-7afc-4148-a98b-9ef26cb1000d · outbound

This paper cites Generative Agents: Interactive Simulacra of Human Behavior.

Interpretable Risk Mitigation in LLM Agent Systems Generative Agents: Interactive Simulacra of Human Behavior

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.028670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de77e093-1471-462a-b0a6-a927f6729dc5 · outbound

This paper cites TinyClick: Single-Turn Agent for Empowering GUI Automation.

Interpretable Risk Mitigation in LLM Agent Systems TinyClick: Single-Turn Agent for Empowering GUI Automation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.033414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73a4ef3f-38c0-44df-85f6-445319704ac3 · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.231251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 35196dd2-37eb-4576-a6c2-b40e2da03ea4 · outbound

This paper cites Effect of private deliberation: Deception of large language models in game play.

Interpretable Risk Mitigation in LLM Agent Systems Effect of private deliberation: Deception of large language models in game play

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.216654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a70cb5aa-ff92-409f-b95a-3405b51bbf27 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Interpretable Risk Mitigation in LLM Agent Systems GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.047108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5a5b1b9-7b0f-427c-973e-a741a2cd28cd · outbound

This paper cites A primer in BERTology: What we know about how BERT works.

Interpretable Risk Mitigation in LLM Agent Systems A primer in BERTology: What we know about how BERT works

Reference 54

Resolution: malformed identifier; no resolver link, observed 2026-08-15T21:11:02.051703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb2fe07f-6a82-4fb7-bc5a-7b4cefa20efd · outbound

This paper cites Research priorities for robust and beneficial artificial intelligence.

Interpretable Risk Mitigation in LLM Agent Systems Research priorities for robust and beneficial artificial intelligence

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.201675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7a2cf6c4-3cb3-42c1-a6c5-e33c3fd83511 · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.185336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 95101970-bd83-42b3-bfc5-703b311591ce · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools.

Interpretable Risk Mitigation in LLM Agent Systems Toolformer: Language Models Can Teach Themselves to Use Tools

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.064856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6167c9-4a5f-46af-b08b-065532a5c700 · outbound

This paper cites An evolutionary model of personality traits related to cooperative behavior using a large language model.

Interpretable Risk Mitigation in LLM Agent Systems An evolutionary model of personality traits related to cooperative behavior using a large language model

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.170463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0b622b1d-44e4-43db-bc95-870dd9ca5525 · outbound

This paper cites A comparative analysis of the definitions of autonomous weapons systems.

Interpretable Risk Mitigation in LLM Agent Systems A comparative analysis of the definitions of autonomous weapons systems

Reference 59

Resolution: verified exact; doi, observed 2026-08-15T21:11:02.190554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 54cdc25e-dcbe-4a06-a3ca-a0b083ec66e7 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Interpretable Risk Mitigation in LLM Agent Systems Gemma: Open Models Based on Gemini Research and Technology

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.078502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e70192c0-2fa3-4d26-9e99-25bce4521ab8 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Interpretable Risk Mitigation in LLM Agent Systems Gemma 2: Improving Open Language Models at a Practical Size

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.082737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 625f59c6-0eef-406d-9cf0-d8c92c8ef449 · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet.

Interpretable Risk Mitigation in LLM Agent Systems Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.087316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b2ebf77-d4d1-47eb-846b-c88fd4d56a1d · outbound

This paper cites Moral alignment for llm agents.

Interpretable Risk Mitigation in LLM Agent Systems Moral alignment for llm agents

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.143335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f523afad-184f-41ef-9a0e-57e19a11c506 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Interpretable Risk Mitigation in LLM Agent Systems LLaMA: Open and Efficient Foundation Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.098429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ac90b8-2d66-452e-9693-66c10e7d314b · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Interpretable Risk Mitigation in LLM Agent Systems Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.104902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ce1bc9-e4d8-4904-9888-9de2d34c5479 · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

Interpretable Risk Mitigation in LLM Agent Systems GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.109561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2942ef8-188f-4e1f-a44b-0747ba8e3471 · outbound

This paper cites Mobile-agent: Autonomous multi-modal mobile device agent with visual perception,.

Interpretable Risk Mitigation in LLM Agent Systems Mobile-agent: Autonomous multi-modal mobile device agent with visual perception,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.127797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e8c5f846-e91b-401e-80a4-0fd5d73e1194 · outbound

This paper cites Dai, and Quoc V Le.

Interpretable Risk Mitigation in LLM Agent Systems Dai, and Quoc V Le

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:11:03.112312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9aac0e58-4508-4dce-b103-c860ac6c28f4 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Interpretable Risk Mitigation in LLM Agent Systems Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.128289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cea8ac7-27e1-49cf-b37d-d6744ff11b68 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Interpretable Risk Mitigation in LLM Agent Systems ReAct: Synergizing Reasoning and Acting in Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.133411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647ac5ed-565f-4692-8bee-b21bc1834a89 · outbound

This paper cites AppAgent: Multimodal Agents as Smartphone Users.

Interpretable Risk Mitigation in LLM Agent Systems AppAgent: Multimodal Agents as Smartphone Users

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.140648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d30244-b423-4420-bcc9-fbd665b74b6d · outbound

This paper cites Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception.

Interpretable Risk Mitigation in LLM Agent Systems Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.118923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10bb76ee-bc2d-40f4-babf-40043502314b · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Interpretable Risk Mitigation in LLM Agent Systems Representation Engineering: A Top-Down Approach to AI Transparency

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.149478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1633c79-0375-4295-bfa3-8325c644a49a · outbound

This paper cites You Only Look at Screens: Multimodal Chain-of-Action Agents.

Interpretable Risk Mitigation in LLM Agent Systems You Only Look at Screens: Multimodal Chain-of-Action Agents

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:02.145319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d843c580-4512-4d8f-a3a6-6b41724a5ec6 · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.984893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671ed4ec-d1ad-4d99-97f8-e0d15322b52b · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Interpretable Risk Mitigation in LLM Agent Systems Measuring Mathematical Problem Solving With the MATH Dataset

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T21:11:01.925637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1e14ac-f124-489b-84f4-00a88d7ea70d · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.474249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 98fbd528-7341-4dfe-92d5-440307b35277 · outbound

This paper cites an unresolved cited work.

Interpretable Risk Mitigation in LLM Agent Systems Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:11:03.276283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation b72a9458-11dc-47d1-84f0-f77d9122b3d6 · inbound

A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy cites this paper.

A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy Interpretable Risk Mitigation in LLM Agent Systems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:51:56.450815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b7081ac-e99d-43fc-be2e-190be39eed65 · inbound

LLM Harms: A Taxonomy and Discussion cites this paper.

LLM Harms: A Taxonomy and Discussion Interpretable Risk Mitigation in LLM Agent Systems

Reference 189

Resolution: verified exact; arxiv_id, observed 2026-05-17T00:31:24.636618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 84d058c8-51a1-4859-970e-8b0c97117aac · inbound

LLM Harms: A Taxonomy and Discussion cites this paper.

LLM Harms: A Taxonomy and Discussion Interpretable Risk Mitigation in LLM Agent Systems

Reference 189

Resolution: unresolved; no resolver link, observed 2026-08-03T18:19:27.337242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.