Paper Citation Record · LEDGER

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

As of 4 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2604.19485.

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

pith.paper-citation-record.v1
2604.19485 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:00:10.404757Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-25T21:04:09.237686Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T19:40:07.675000Z

Reference resolution

41 of 41 outbound references displayed

verified exact26
verified fuzzy13
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 070ed26d-0fa9-424f-9df1-bf4ba480d6f7 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:42:22.769824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ea8e235b-a331-4da2-a83a-26c8f447d281 · outbound

This paper cites Averaged-dqn: Variance reduction and stabi- lization for deep reinforcement learning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Averaged-dqn: Variance reduction and stabi- lization for deep reinforcement learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.607300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b6d58115-abd7-41f2-b3a2-22602d0f85a2 · outbound

This paper cites Gui-shepherd: Reliable process reward and verification for long-sequence gui tasks, September 2025.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Gui-shepherd: Reliable process reward and verification for long-sequence gui tasks, September 2025

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:12.588601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 332ede39-4f3e-4274-a4c8-71f714fb5e3e · outbound

This paper cites Learning without critics? revisiting grpo in classical reinforcement learning environments.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Learning without critics? revisiting grpo in classical reinforcement learning environments

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:11.525899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 679eeca9-d734-4a81-b785-a0934aa19ab0 · outbound

This paper cites The frozen lake problem.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training The frozen lake problem

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.600144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ff2ef797-b3f5-4974-b805-8c16a1d9172b · outbound

This paper cites an unresolved cited work.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Unresolved cited work

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:13.179286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0d80652e-ef3e-4c30-b284-ee1ac9ecff8f · outbound

This paper cites Octobench: Benchmarking scaffold-aware instruction following in repository-grounded agentic coding.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Octobench: Benchmarking scaffold-aware instruction following in repository-grounded agentic coding

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:11.316396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9eb9b35f-10ab-4888-a16d-22fd91e52edc · outbound

This paper cites Agentic reinforced policy optimization.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Agentic reinforced policy optimization

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.596152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87b51482-1e6f-432c-a924-af2097d3298d · outbound

This paper cites Cl-bench: A benchmark for context learning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Cl-bench: A benchmark for context learning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:11.131519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0a1771d8-2915-4fb5-aa69-ac94eba01aa5 · outbound

This paper cites Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:13.306057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0fe7c71c-3124-4601-ad39-b82e6c7743c7 · outbound

This paper cites doi: 10.1038/s41586-025-09422-z.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training doi: 10.1038/s41586-025-09422-z

Reference 11

Resolution: verified exact; doi, observed 2026-05-10T03:03:36.750129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 604f67c0-6e79-480a-80db-ac9a988ea258 · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:21:45.673967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 261bab36-5b15-41f4-8a4a-8e3d40d46b55 · outbound

This paper cites Towards understanding the optimization landscape of grpo and its variants.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Towards understanding the optimization landscape of grpo and its variants

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.590129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 73a1a290-0e49-44ed-a61a-904f345cb386 · outbound

This paper cites Sokoban: Enhancing general single-agent search methods using domain knowledge , journal =.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Sokoban: Enhancing general single-agent search methods using domain knowledge , journal =

Reference 14

Resolution: verified exact; doi, observed 2026-05-10T03:03:36.747580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 50c061d6-43fa-463f-b808-620fd33aec06 · outbound

This paper cites A new approach to linear filtering and prediction problems.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training A new approach to linear filtering and prediction problems

Reference 15

Resolution: verified exact; doi, observed 2026-05-10T03:03:36.745652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b52747d3-c75b-4382-a88f-5cc3f1972bfd · outbound

This paper cites Unifying ppo, dpo, and grpo: A theoretical and empirical study on llm post-training, November 2025.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Unifying ppo, dpo, and grpo: A theoretical and empirical study on llm post-training, November 2025

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.584422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 649c0255-4eee-4e12-89dd-4635c3126c8f · outbound

This paper cites Mm-doc-r1: Training agents for long document visual question answering through multi-turn reinforcement learning, April 2026.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Mm-doc-r1: Training agents for long document visual question answering through multi-turn reinforcement learning, April 2026

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.586406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7396d07c-85f9-4598-a8ed-c75c020622f8 · outbound

This paper cites Proximal policy optimization with adaptive generalized advantage estimate: Critic- aware refinements.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Proximal policy optimization with adaptive generalized advantage estimate: Critic- aware refinements

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.588276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 52df4864-6f2b-440c-af71-48e8a41e4311 · outbound

This paper cites OpenAI o1 System Card.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training OpenAI o1 System Card

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:10.654980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 538fc613-7358-4188-bcca-00317d9669f3 · outbound

This paper cites An Elementary Introduction to Kalman Filtering.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training An Elementary Introduction to Kalman Filtering

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:46:12.249347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d364b24c-9873-4bd4-bda2-afe96b0aeef1 · outbound

This paper cites Qwen2.5 Technical Report.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Qwen2.5 Technical Report

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:12.105785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 43ac8606-efac-4d49-8654-aebead90d3e9 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Qwen3.5: Towards native multimodal agents, February 2026

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.592566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cadac5ea-75f9-442a-93de-d8ae094f112d · outbound

This paper cites The nuts and bolts of deep rl research, December 2016.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training The nuts and bolts of deep rl research, December 2016

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.582364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 08c7aba5-b672-4e70-847d-eafbee323e6b · outbound

This paper cites Proximal Policy Optimization Algorithms.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Proximal Policy Optimization Algorithms

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:12.712352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b008bad2-a9b0-422f-a879-59dfd3f8a87f · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:11.006886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 04d1690d-680f-4dac-8a2a-8c8b2bae3462 · outbound

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

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:11.484943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2beded7a-e5e3-42dd-ade5-0726477dbc3b · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:39:15.970362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 121a48e8-329f-4a80-986e-58ba0a5f12b9 · outbound

This paper cites an unresolved cited work.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-22T18:31:56.594358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ae39a11b-b775-4b53-9ea8-f83edfa691d0 · outbound

This paper cites OpenAI GPT-5 System Card.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training OpenAI GPT-5 System Card

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:12.427917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9de7384c-f87e-4d37-b39a-f70f4276010e · outbound

This paper cites Policy gradient meth- ods for reinforcement learning with function approximation.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Policy gradient meth- ods for reinforcement learning with function approximation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.598210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dac46bdd-4f89-495d-b50c-492ca214988c · outbound

This paper cites Reft: Reasoning with reinforced fine-tuning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Reft: Reasoning with reinforced fine-tuning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.605493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation aeed9c43-44f7-4d04-ac8c-0b077318213c · outbound

This paper cites R e FT : Reasoning with reinforced fine-tuning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training R e FT : Reasoning with reinforced fine-tuning

Reference 32

Resolution: metadata mismatch; doi, observed 2026-05-10T03:03:36.754019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 799d480a-dd61-466a-a561-bff8d4801995 · outbound

This paper cites Enhancing llm-based search agents via contribution weighted group relative policy optimization, April.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Enhancing llm-based search agents via contribution weighted group relative policy optimization, April

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.602025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 62ffc7c2-1021-4394-bd72-5fc45a609449 · outbound

This paper cites Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:13.099355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f2bb9c72-46d1-47e0-917c-46b24afd5490 · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:13:34.687091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 479d39b5-3732-47da-91e6-59dcba4a505f · outbound

This paper cites Williams.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Williams

Reference 36

Resolution: verified exact; doi, observed 2026-05-10T03:03:36.752206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec79021b-ecc1-44a4-a376-adf6d1657c86 · outbound

This paper cites Qwen3 Technical Report.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Qwen3 Technical Report

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:13.749355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 849d9d33-71e8-4e6e-8cfc-14f36a3d2ac5 · outbound

This paper cites Narasimhan.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Narasimhan

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T18:31:56.603672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4c688259-e04a-42df-b0b1-1e60db5871f8 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:13.509807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 337a1bbe-7e7d-4c1c-99fd-a31b223f6a84 · outbound

This paper cites Secrets of RLHF in Large Language Models Part I: PPO.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Secrets of RLHF in Large Language Models Part I: PPO

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-17T13:17:43.137115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 178facb6-b1e2-4c5c-9dc9-07f81c80c4a5 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training Instruction-Following Evaluation for Large Language Models

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-11T12:46:12.866351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 3836ffba-fb46-4ec7-9a06-ecfcd9361482 · inbound

BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents cites this paper.

BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T19:40:07.676769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.