Paper Citation Record · LEDGER

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

As of 20 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 9 inbound Pith citation observations for arXiv:2505.02686.

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

pith.paper-citation-record.v1
2505.02686 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:47:59.942231Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

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

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T12:58:02.233748Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T07:59:40.123100Z

Reference resolution

24 of 24 outbound references displayed

verified exact1
verified fuzzy1
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 02fa8ef8-e6f9-482a-aaa8-a6a12c1465fb · outbound

This paper cites Concrete Problems in AI Safety.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Concrete Problems in AI Safety

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.844459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5568689e-7b10-47bb-8d07-1fb35de0a9ee · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.853822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1290362-3a1f-4b42-8629-2ef1c05a7f2d · outbound

This paper cites CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.858369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 334a5b08-4e21-4690-9374-120a8a4265a3 · outbound

This paper cites In The Twelfth International Conference on Learning Representations.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards In The Twelfth International Conference on Learning Representations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:48:00.553206Z

Source-reported events for the cited work

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

Observation af1a094b-f262-4281-a1bf-9e227f1dd2af · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Training Language Models to Self-Correct via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.869987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3108e031-008a-4345-9fa0-ee2c5a40d36b · outbound

This paper cites In The Twelfth Inter- national Conference on Learning Representations.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards In The Twelfth Inter- national Conference on Learning Representations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.873946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e5818d-8133-40f4-894d-5a13cdce061a · outbound

This paper cites Generative Reward Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Generative Reward Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.877697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 704c9448-cedf-4e2e-a8a0-3e46cadbbbfc · outbound

This paper cites GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.882096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76c2ce46-1a46-40e1-8947-a9eb9308992a · outbound

This paper cites GPT-4 Technical Report.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards GPT-4 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.886298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ca95a0f-f308-4e95-a3d5-653fc7fefe31 · outbound

This paper cites Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.894438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ce98d7-9f47-43ad-a4f6-72dbacb48a92 · outbound

This paper cites Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.898459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2609e571-1858-40f8-bdff-b0766b5e2a48 · outbound

This paper cites Towards Cost-Effective Reward Guided Text Generation.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Towards Cost-Effective Reward Guided Text Generation

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-08-16T00:48:00.222120Z

Source-reported events for the cited work

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

Observation 668e6ea7-8665-4257-bf2b-4cca0dc65295 · outbound

This paper cites arXiv preprint arXiv:2407.04615.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards arXiv preprint arXiv:2407.04615

Reference 18

Resolution: verified exact; raw_fallback, observed 2026-08-16T00:48:00.185769Z

Source-reported events for the cited work

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

Observation 823e038e-2e65-4052-babd-e4499e8ef3eb · outbound

This paper cites mDPO: Conditional Preference Optimization for Multimodal Large Language Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards mDPO: Conditional Preference Optimization for Multimodal Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.920486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd1e7523-399a-4c2d-beb4-2658e816daa7 · outbound

This paper cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.925135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e9bbb2-fb5c-44c9-b6d2-e1aa7f4966f6 · outbound

This paper cites On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.929137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617e7a27-5af9-45f3-91ed-3234000289e1 · outbound

This paper cites Advances in Neural Information Processing Systems, 36:41618–41650.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Advances in Neural Information Processing Systems, 36:41618–41650

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.934306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f885e547-7aa9-4779-bbd9-71218d29e38d · outbound

This paper cites Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.938066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2394fba1-3d86-4feb-b22a-07787f631ac8 · outbound

This paper cites Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.942231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5e3fe7-c7ea-4b47-9b40-552cf6b86b5d · outbound

This paper cites Self-critiquing models for assisting human evaluators.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Self-critiquing models for assisting human evaluators

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.907338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d380dc8c-6a17-472f-89ba-b03aa0e6d3e8 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.890088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64dff9b-1e48-44a6-97d1-c7c9e877a38b · outbound

This paper cites Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.839673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3d93e4c-8845-44e2-8a86-98ef30b624a8 · outbound

This paper cites Critique-out-Loud Reward Models.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards Critique-out-Loud Reward Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.849111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65b86e6-2d33-46a5-b87e-37a75716c1b9 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T00:47:59.862170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation cc987656-7d73-4688-9723-f97ce0a6b9d0 · inbound

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge cites this paper.

AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T12:58:02.233748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d052a9-dcb5-45c1-9584-344c8260366a · inbound

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation cites this paper.

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:39:19.201927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b08205ac-ba61-43a9-a7d5-dbcb2efed3b2 · inbound

Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning cites this paper.

Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T12:40:13.070016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af4c72b2-bc22-40cc-85b2-9cb08932bbd9 · inbound

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding cites this paper.

ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T11:52:04.806540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba0db544-a3dc-49a4-99ab-304f93204ed0 · inbound

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings cites this paper.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.797401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9257381-076a-420b-acae-22465db6a9cc · inbound

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning cites this paper.

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:16:53.795613Z

Source-reported events for the cited work

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

Observation fc378cd4-d001-44b5-98fd-4880a08afbb8 · inbound

Unsupervised Hallucination Detection by Inspecting Reasoning Processes cites this paper.

Unsupervised Hallucination Detection by Inspecting Reasoning Processes Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T18:25:37.408457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44eb936b-cc01-450d-a763-d02363a1ccd7 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:56:13.574362Z

Source-reported events for the cited work

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

Observation 5ceacf62-af66-4d4e-9ce2-3b095fa951ad · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 228

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:40.124708Z

Source-reported events for the cited work

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