Paper Citation Record · LEDGER

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

As of 23 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 12 inbound Pith citation observations for arXiv:2506.08745.

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

pith.paper-citation-record.v1
2506.08745 v1

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:09:46.121588Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:29:00.494940Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T13:59:51.882252Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy23
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b6ffe7a6-8cd9-4dea-9d5d-dd5cad7aa535 · outbound

This paper cites Kakade, Jason D.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Kakade, Jason D

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.922731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 33bb0019-910d-4abe-974c-3fdef402e725 · outbound

This paper cites Open r1: Evaluating llms on uncontaminated math competitions, 2025.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Open r1: Evaluating llms on uncontaminated math competitions, 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.913745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 349a80c7-031e-4bf9-b36e-80b6ca054ddd · outbound

This paper cites Program Synthesis with Large Language Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Program Synthesis with Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.339097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a028dc47-6b3c-461a-b440-d01b6c095bd8 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.395768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 126ac31b-a149-4f20-a242-22e69feca703 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Evaluating Large Language Models Trained on Code

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.459366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a66c95-c231-4ac5-800a-9fb4f645469d · outbound

This paper cites An Empirical Study on Eliciting and Improving R1-like Reasoning Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning An Empirical Study on Eliciting and Improving R1-like Reasoning Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.527494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96f279b-e9e2-4748-8db7-cbbe8ca149b3 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.531213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ace5b57-f3d8-47b4-854e-7baf906a026f · outbound

This paper cites The Llama 3 Herd of Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.533735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de5575b2-157c-4405-a3db-3e040724983f · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.537444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f8b083-dc55-41ed-aaa8-cce6433666c1 · outbound

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:42.613608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 740110bb-d645-412c-a1e5-969cf9887c27 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Olympiadbench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.903681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 47db5fb1-f488-460d-a6a4-2b79b25aeae2 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Measuring mathematical problem solving with the MATH dataset

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.895231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8f58d985-37a9-48c1-be99-122ef30061de · outbound

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.068905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a9ab83-840e-422d-820b-e131a5396b53 · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.246700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f59237a1-bee6-407f-a99b-ea33077367e3 · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.415963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68bf5204-e622-4186-a76a-b84f075529da · outbound

This paper cites OpenAI o1 System Card.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning OpenAI o1 System Card

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.589672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0e0c34-3cd6-4d97-ab62-faadd798ef38 · outbound

This paper cites Buy 4 REINFORCE samples, get a baseline for free! In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop, 2019.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Buy 4 REINFORCE samples, get a baseline for free! In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop, 2019

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.886118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ba7da1c7-439b-41fe-a38b-b24b3222e832 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Efficient memory management for large language model serving with pagedattention

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.874897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d58092d-d4fc-4dee-97c8-cca1226af5c6 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.878319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d523d22-44c7-4159-8605-808ce22af111 · outbound

This paper cites Numinamath, 2024.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Numinamath, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:43.926312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c71c6a20-c3f8-4038-9297-01d8d6730a0b · outbound

This paper cites Let’s verify step by step.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Let’s verify step by step

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.860484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e1c935f6-3a28-48d5-aa9a-b50a8efa91e9 · outbound

This paper cites A Survey of Direct Preference Optimization.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning A Survey of Direct Preference Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.129023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59a01924-d375-4698-afa9-7e01cd44e84c · outbound

This paper cites Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.200132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac2164ab-115b-4381-b36e-a55838303da1 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.269991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85670879-67ff-43f4-9d9c-f41cc542d951 · outbound

This paper cites On the global convergence rates of softmax policy gradient methods.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning On the global convergence rates of softmax policy gradient methods

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.851299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a7d0a55c-b43f-4d58-98ad-299082650a33 · outbound

This paper cites an unresolved cited work.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:09:46.761702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dfad0528-64af-4b13-bad9-d394c6b8df70 · outbound

This paper cites Iterative reasoning preference optimization.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Iterative reasoning preference optimization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.751714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0d617e2b-74d7-46c1-8a74-dda527e8d774 · outbound

This paper cites Are NLP models really able to solve simple math word problems? InNorth American Chapter of the Association for Computational Linguistics, 2021.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Are NLP models really able to solve simple math word problems? InNorth American Chapter of the Association for Computational Linguistics, 2021

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.741637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d553303b-f8d8-4160-b70d-91155988e8dc · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Manning, Stefano Ermon, and Chelsea Finn

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.731168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0fab6a5d-2b04-45ea-97a3-48a1e71374dd · outbound

This paper cites Semantic cosine similarity.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Semantic cosine similarity

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.722065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ddc33db8-3652-4bdf-8cbd-be304684d6a0 · outbound

This paper cites What makes a reward model a good teacher? an optimization perspective.arXiv preprint arXiv:2503.15477, 2025.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning What makes a reward model a good teacher? an optimization perspective.arXiv preprint arXiv:2503.15477, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.700943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4faffc-9300-4686-b4b0-3249f98dd90d · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.769436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3ca9b9-f63c-42e7-bb4b-d15eb909844e · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Gpqa: A graduate-level google-proof q&a benchmark

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.709087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation af519356-a0cd-44dd-98d6-0ae87e455b75 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Proximal Policy Optimization Algorithms

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:44.871042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bca96c70-9f78-4100-bbdf-d6bd0ef41128 · outbound

This paper cites A mathematical theory of communication.The Bell system technical journal, 1948.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning A mathematical theory of communication.The Bell system technical journal, 1948

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.698740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6ce762ba-95d2-4297-88e7-3e04074a7a03 · outbound

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.000333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f5da95-4b79-4e1e-ba65-f83acba760b6 · outbound

This paper cites Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.062113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255ae497-a8d3-4e96-987b-23795bdf76c8 · outbound

This paper cites MIT press Cambridge, 1998.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning MIT press Cambridge, 1998

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.112502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a48ae3-e6ce-46a4-9b33-513fc885edc4 · outbound

This paper cites Commonsenseqa: A question answering challenge targeting commonsense knowledge.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Commonsenseqa: A question answering challenge targeting commonsense knowledge

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.684681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ed5c02dc-80b9-4fe9-9eb3-558a69b6038d · outbound

This paper cites Le, Ed H.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Le, Ed H

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.675301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation baf741f9-462f-4292-aa7b-819939d4589a · outbound

This paper cites Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.364256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706440a4-c0a9-47c8-96af-1477ac5189b2 · outbound

This paper cites Wong, Zhuosheng Zhang, and Rui Wang.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Wong, Zhuosheng Zhang, and Rui Wang

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.665635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c10d9300-976e-4ae8-8d9f-0ba9d28f4d26 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.655371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 84ddd584-f7dc-4d90-beb6-3439d62ea7a8 · outbound

This paper cites CREAM: Consistency Regularized Self-Rewarding Language Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning CREAM: Consistency Regularized Self-Rewarding Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.503921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ff06b2-70d6-4386-b387-4bacf9fbf833 · outbound

This paper cites Chi, Quoc V.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Chi, Quoc V

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.645771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1fef196a-87d2-4433-a6a7-37af59368ef7 · outbound

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.585513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b844e0e9-3376-412c-89aa-c3ac0f50d2bd · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.619823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8ec851-bcbe-4610-825e-f5be039ea645 · outbound

This paper cites Self-rewarding correction for mathematical reasoning.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Self-rewarding correction for mathematical reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.657899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea577258-48cf-4c2f-b79d-f26916e0f3e0 · outbound

This paper cites Qwen2.5 Technical Report.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Qwen2.5 Technical Report

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.688442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f7a275-2495-411c-a8cd-15faa612de94 · outbound

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

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.745522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e43cf3-1427-4cee-a808-e6800a55c9ed · outbound

This paper cites Self-rewarding language models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Self-rewarding language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.635670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 85a54cc2-bdcb-4eea-9f1e-d18d4b028f3a · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.798657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e11b935-4602-4260-818a-7337de2eb813 · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.826337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2ffa49-c387-402e-bb6f-05bb86a0dde2 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.849450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99f6ab8-b206-410d-9992-fa579703938d · outbound

This paper cites R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.877654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ca236c-8010-4364-b52b-f308d2ab6a58 · outbound

This paper cites Sample efficient reinforcement learning with reinforce.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Sample efficient reinforcement learning with reinforce

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.626201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 871a9734-5061-49f7-98a0-123e3038f3d5 · outbound

This paper cites Reasoning with Reinforced Functional Token Tuning.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Reasoning with Reinforced Functional Token Tuning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.933741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96c8c71-2b16-4466-af1d-22da45d8d444 · outbound

This paper cites Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:45.969598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fd01d9-4a5a-4067-8c7f-6140ea62cb82 · outbound

This paper cites Process-based Self-Rewarding Language Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Process-based Self-Rewarding Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:46.000207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b1f075-2d3f-4a02-bc76-f2266f53f3a7 · outbound

This paper cites Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:46.031769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1fcc14-1af2-4ead-8c0c-fe95686c89db · outbound

This paper cites Calibrated self-rewarding vision language models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Calibrated self-rewarding vision language models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.614123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b4962ff6-9a42-4688-8290-a53355ebb185 · outbound

This paper cites Landscape of thoughts: Visualizing the reasoning process of large language models.arXiv preprint arXiv:2503.22165, 2025.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Landscape of thoughts: Visualizing the reasoning process of large language models.arXiv preprint arXiv:2503.22165, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:46.096209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba2c7f2-b2cc-4807-8c01-8a8bf8181b62 · outbound

This paper cites Texygen: A benchmarking platform for text generation models.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning Texygen: A benchmarking platform for text generation models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:09:46.601801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e93e34ce-8ff9-4559-8d0c-652a94ae0a90 · outbound

This paper cites BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:46.113846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d13d38-dc1c-46a8-8c78-dbf3c121cc03 · outbound

This paper cites TTRL: Test-Time Reinforcement Learning.

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning TTRL: Test-Time Reinforcement Learning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T05:09:46.121588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 29319d30-5e71-4196-a3bf-7d2e642e1d67 · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 180

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:14.968757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9cadc56b-68ff-4aa3-b874-4412ffc301f0 · inbound

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents cites this paper.

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T19:29:00.494940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ecaf77b-8d39-4576-b78f-eca6fc09c686 · inbound

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training cites this paper.

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:20:57.469347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24083e58-3a7d-4795-ad66-57b4b709d172 · inbound

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data cites this paper.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.961406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 10de83ea-bbcd-421c-9cd4-af79fe64ff8e · inbound

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces cites this paper.

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:05:03.819469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2b93e0d7-a109-4f6d-b3a5-c4f04b6f73ab · inbound

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards cites this paper.

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:04:01.335231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 87aaad09-9d25-4276-aa0a-da8b8d618830 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:46:14.369084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cd01867c-1484-4581-9ce0-6109352f8bd9 · inbound

Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots cites this paper.

Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-02T07:26:46.234876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3c3e53ac-6859-4942-a940-366d111b5910 · inbound

GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling cites this paper.

GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T06:06:40.790106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ed2c3dae-401c-4cf9-9c43-135827c3186a · inbound

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment cites this paper.

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 61

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T14:08:21.659582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ddbafa54-e33e-4dc9-9f48-ee9e5c8f1759 · inbound

Reinforcement Learning without Ground-Truth Solutions can Improve LLMs cites this paper.

Reinforcement Learning without Ground-Truth Solutions can Improve LLMs Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:59:51.883679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c0481c5-6659-4e70-a0b2-28879ea86c06 · inbound

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation cites this paper.

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T09:29:14.105502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.