Paper Citation Record · LEDGER

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

As of 16 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 3 inbound Pith citation observations for arXiv:2504.20157.

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

pith.paper-citation-record.v1
2504.20157 v2

Coverage vector

measured 78 of 78 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:40:09.533305Z

measured 81 of 81 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:29:18.049711Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-13T06:07:56.781634Z

Reference resolution

78 of 78 outbound references displayed

verified exact1
verified fuzzy15
unresolved62
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 84014ee3-0a43-46f5-b326-d6970b87b155 · outbound

This paper cites Ahmadian, C.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Ahmadian, C

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.128421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4306b0ca-f5f8-4992-8f57-d901d427a5b4 · outbound

This paper cites Amodei, C.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Amodei, C

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.884168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a224da52-802f-42ba-b81f-db6ed05552aa · outbound

This paper cites Concrete Problems in AI Safety.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Concrete Problems in AI Safety

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.141124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 556e3ce8-83e2-4569-969f-8804d3cc9109 · outbound

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

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.146832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10bd2885-16aa-4cf9-9b8a-fa048e6f08a9 · outbound

This paper cites Buckley, T.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Buckley, T

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.868225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 91c60746-0dce-4ca3-a41b-b26db3800892 · outbound

This paper cites ODIN: Disentangled Reward Mitigates Hacking in RLHF.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models ODIN: Disentangled Reward Mitigates Hacking in RLHF

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.158251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae0345da-19bc-4bd4-81e0-f040ef5bffa9 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.852486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 50b31a4f-c1f1-43c9-a793-b8ba75fb26f4 · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.169269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ef45af-468c-4eac-8426-7e477df43f2b · outbound

This paper cites Coste, U.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Coste, U

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.836698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 836b619c-f099-4806-bf18-aa63d08c53d9 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.820404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ae088c77-19a0-410f-835a-817d8ce11952 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.184730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66984877-6b63-4282-ba84-e1fa7d93d77a · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.189989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 192bcb4f-0014-4344-86d5-96a3f0016df2 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.804793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f2d9a440-6136-4c47-9383-4967c4f8086f · outbound

This paper cites Efklides.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Efklides

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.788673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e1af0d2c-812f-41fd-9a01-dd322fcab31e · outbound

This paper cites Eisenstein, C.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Eisenstein, C

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.772380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f4431f81-cd12-44f6-bb02-e79f62bbd885 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models KTO: Model Alignment as Prospect Theoretic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.208936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57dbda2-dc2e-4c8b-8c38-bf3675930d1a · outbound

This paper cites Everitt, M.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Everitt, M

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.754664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 69bd380b-f029-45cd-b87c-8e663f6923cc · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.738502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1088a2dc-d7d6-4b3d-aafb-dbb2db24837c · outbound

This paper cites The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.223889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 622f78c8-129d-48ff-a38f-179609261787 · outbound

This paper cites Reward Shaping to Mitigate Reward Hacking in RLHF.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.228950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c964a05-3372-4c03-81cd-062246a087ae · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.722228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 972e2a40-d167-4af7-9275-05ca3f9ee066 · outbound

This paper cites Hamner, J.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Hamner, J

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.706274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9a360b64-3cbf-43bd-8b13-02fa13c14d9c · outbound

This paper cites Hendrycks, C.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Hendrycks, C

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.689981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4b777d64-80d6-4460-95d2-25b7b5664f22 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.249327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4d5521-3aff-4dd4-b14c-0c29b73a4b73 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.254238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1ad9198-c9d1-4078-ab47-40aee5bc693b · outbound

This paper cites Kornilova and V.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Kornilova and V

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.259920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38cfb96-0bc9-4eea-a2aa-15bd1d42b31b · outbound

This paper cites Krakovna, J.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Krakovna, J

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.265135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433df192-df45-420f-9bb0-346297af1b6e · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.663066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5f8948f6-c1b9-43c5-a354-fc31c7dbf8ca · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.647596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 65d092b0-0a66-4b03-80bc-38d1630052be · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.284787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb6f3bd-3dd9-4bce-8e61-4dd24a6dfc98 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.619821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2b6b871e-def0-4485-8e08-94be64156b19 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.604313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2a05bfa3-4df1-45af-a08b-56cb3225c0e6 · outbound

This paper cites RRM: Robust Reward Model Training Mitigates Reward Hacking.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models RRM: Robust Reward Model Training Mitigates Reward Hacking

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.300373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35f4bdc6-319e-43c5-9303-46afe503f3c0 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.588317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8facfa69-c929-44de-be2e-537ca11185c1 · outbound

This paper cites Lourie, R.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Lourie, R

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.572366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a83fbe96-8807-4a2b-83df-d972bad9ed09 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.556775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9e4a206-746d-4a89-bc50-5f3bbb6f1d3e · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.540436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7b1aaf42-37b4-471c-ae6c-3b964cf90611 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.524150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 527e7dc8-f5f6-4d90-8a32-520471788536 · outbound

This paper cites Metcalfe and N.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Metcalfe and N

Reference 40

Resolution: verified exact; doi, observed 2026-08-16T05:40:09.598519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a58260a0-9af0-45cf-8590-43ca5d4e1164 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.506102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2294f5e1-732b-40e7-910a-3e74daaa4d19 · outbound

This paper cites The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.338975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68bc6e34-2ae4-4707-a5da-c381600b1957 · outbound

This paper cites Ouyang, J.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Ouyang, J

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.488096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1671728b-5791-4991-8af3-1404c6cb7c89 · outbound

This paper cites Ouyang, J.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Ouyang, J

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.471645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b11e6543-9da9-4bbd-a492-8597831bab04 · outbound

This paper cites Ouyang, J.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Ouyang, J

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.454776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bcb71774-95aa-431c-bfb5-00ae317dee4e · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.437918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b014d8c6-a3ac-4f19-95ae-579bfc4cf962 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.363769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd4b6a38-51b6-4861-8ce8-b0683ac52398 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.422198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cdf3ab89-eaf0-420f-a33d-d487e4804a56 · outbound

This paper cites RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.374182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11df0c3d-e5ee-40f6-9677-7e0438431df9 · outbound

This paper cites MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.379491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b76ba7ae-bc15-47c3-ad44-1e5664272e99 · outbound

This paper cites Perez, S.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Perez, S

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.384702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0d625eb-b103-4a56-b950-355b7800b92d · outbound

This paper cites Qwen2.5 Technical Report.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Qwen2.5 Technical Report

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.389446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b2ac55e-fa62-4471-a7a6-955281384036 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.394787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce64f43f-f56f-4ceb-a41b-946b213c5fc1 · outbound

This paper cites Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.399353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac2ff3d-b2bc-488d-a9f0-6c7e6e41f189 · outbound

This paper cites Verbosity Bias in Preference Labeling by Large Language Models.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Verbosity Bias in Preference Labeling by Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.404427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffa1d05-eec1-4e60-afd8-78932d7724dc · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.414460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 945a2281-cd88-478f-a281-cabf37e7366b · outbound

This paper cites Sharma, M.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Sharma, M

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.378237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0af90142-28ef-42f0-af13-5cf3c4d47bfc · outbound

This paper cites Singhal, T.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Singhal, T

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.361213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e811439f-75ea-4476-9b60-b3b631382a62 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.342362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 22eb0913-acdf-4a0e-b0da-3ae9645d77bd · outbound

This paper cites Stiennon, L.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Stiennon, L

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:40:10.324517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d0391c6e-1b24-4948-9b00-a8c2744aa454 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.306564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ede0c600-1e5e-4546-8b8e-15db8f5c538f · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.290637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 78c37b0b-b751-4d8c-812b-8f2c0eb3be84 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.274336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 88e587cd-4c3b-4ad9-93cb-8ef92bdc6926 · outbound

This paper cites von Werra, Y.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models von Werra, Y

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.453207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb0dfb0-e5f0-41c0-b2a2-4499233940d3 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.248070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 81672bab-2540-4b7e-a93a-9d2bdb0a2356 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.231946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8087916d-e8cb-4716-a863-e32a161a2792 · outbound

This paper cites Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.467576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9725a20f-ecbb-4e9d-b395-b5b8eff154be · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:40:10.215955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d1fea079-aa42-499f-9b4d-ffc4df35466f · outbound

This paper cites Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.477323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e727195b-d96b-45c0-b113-21d25c98ee16 · outbound

This paper cites Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.483189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30273e3a-f987-4b7d-9c49-dd0e691a5f71 · outbound

This paper cites Qwen2 Technical Report.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Qwen2 Technical Report

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.488443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a049343-5f77-4b12-ba85-9963fe750d34 · outbound

This paper cites Self-Rewarding Language Models.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Self-Rewarding Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.493614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f871c059-471c-480a-a2df-30632b8255e1 · outbound

This paper cites Zhang, C.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Zhang, C

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.499053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16fbac64-21f1-4c7b-be01-69dcc5635eaa · outbound

This paper cites Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.503684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91dd55db-cff6-4a6f-b309-b58a9a88d1c6 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models SGLang: Efficient Execution of Structured Language Model Programs

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.508737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28dd2998-59d5-438a-8394-5222b09e945c · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Fine-Tuning Language Models from Human Preferences

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.518689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aa3b570-ab53-40e2-bba8-cbe2d4dd9940 · outbound

This paper cites @esa (Ref.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models @esa (Ref

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.523386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 725ee1b4-4440-437b-a44b-19c7a9fe4673 · outbound

This paper cites an unresolved cited work.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models Unresolved cited work

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.528530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e22da6-d4ce-4a22-b621-5a20094e4d05 · outbound

This paper cites A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety.

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-16T05:40:09.533305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4a11841a-1d3f-494b-b92f-976e3a3625a3 · inbound

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains cites this paper.

Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:07:56.785000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 514714e3-6952-4251-a15e-d7d09cae203f · inbound

Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex cites this paper.

Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Reference 222

Resolution: unresolved; no resolver link, observed 2026-07-31T23:52:09.180660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7112acee-2383-4d63-9ac7-fbb30715048d · inbound

Improving Generalization Robustness of Multimodal RLVR cites this paper.

Improving Generalization Robustness of Multimodal RLVR Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:29:18.049711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.