Paper Citation Record · LEDGER

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

As of 16 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2607.21971.

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

pith.paper-citation-record.v1
2607.21971 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T06:17:30.923859Z

measured 31 of 31 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy0
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 53922a82-2efd-40f5-bf5b-a932d4c9fb47 · outbound

This paper cites Tool-r0: Self-evolving llm agents for tool-learning from zero data.arXiv preprint arXiv:2602.21320,.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Tool-r0: Self-evolving llm agents for tool-learning from zero data.arXiv preprint arXiv:2602.21320,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:27.893513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e454a080-4ae4-404d-a318-2b9023df8b0f · outbound

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

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.286504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6fa36e3-4de7-41e5-a24e-a19dce39c1f2 · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.461299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 000030d2-0b33-4d6f-aa88-676fcb5bbf4e · outbound

This paper cites TACO: Topics in Algorithmic COde generation dataset.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning TACO: Topics in Algorithmic COde generation dataset

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.636771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 435da973-f07f-41fe-a144-ae5e61668802 · outbound

This paper cites s1: Simple test-time scaling.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning s1: Simple test-time scaling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.698988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfd4648f-a578-497b-910d-7a094c0f71ee · outbound

This paper cites AlphaEvolve: A coding agent for scientific and algorithmic discovery.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning AlphaEvolve: A coding agent for scientific and algorithmic discovery

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.779932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d736a13-c85b-4f74-8951-abb03b108e4e · outbound

This paper cites Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.952018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f3796a-0c3e-46af-b599-7674d5e75dbe · outbound

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

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.146347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 173508c7-8ccc-400f-8a0e-1c8cfbaf5784 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning HybridFlow: A Flexible and Efficient RLHF Framework

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.227523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6538a143-6205-42b7-b0ea-e1734f4021e0 · outbound

This paper cites Can Language Models Solve Olympiad Programming?.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Can Language Models Solve Olympiad Programming?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.317498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecfe5ef8-f368-4708-a020-1d19cc1f19c8 · outbound

This paper cites Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.411352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9b24a70-7188-4c75-9263-5862a13fbec2 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.493127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4669a225-09d9-4622-864f-4cb0d61d9aec · outbound

This paper cites Large language model reasoning failures.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Large language model reasoning failures

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.584985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6e34b7-b0d0-4270-8d81-542ffb413ae6 · outbound

This paper cites Under review.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Under review

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.668687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d221d477-c10b-4927-91fe-6ba648b9939b · outbound

This paper cites ThetaEvolve: Test-time Learning on Open Problems.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning ThetaEvolve: Test-time Learning on Open Problems

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.754644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63972755-8e1c-4bd2-b8cb-66c9de8a73bd · outbound

This paper cites LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.782230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c443b250-a9f3-4583-95bd-86a5d31f7d72 · outbound

This paper cites Qwen3 Technical Report.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.938488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d592169-b77b-4224-8570-132ba46210a4 · outbound

This paper cites ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.221262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb439d78-5096-4625-ab82-618defb3f50a · outbound

This paper cites SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.431790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b3f886-63a0-4844-9618-e8ea366327c8 · outbound

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

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Fine-Tuning Language Models from Human Preferences

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.601405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b0629b3-dfb0-46ce-bba4-bd80c8a03f01 · outbound

This paper cites an unresolved cited work.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.923859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2543b24-09ef-4288-bffd-db2be8b8fe91 · outbound

This paper cites A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

Reference 1989

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.106561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0690d2b4-9e15-4ce8-b129-4e2ec6d75196 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Process Reinforcement through Implicit Rewards

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.092385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21158904-90a0-4cd4-874d-a9b7fab6cf84 · outbound

This paper cites Under review.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Under review

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:30.720072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7628df11-b20d-406b-bd58-a5252f404447 · outbound

This paper cites CodeBLEU: a Method for Automatic Evaluation of Code Synthesis.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:29.063792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceee4493-3caf-4ecd-bbb1-9534e9b2cfe0 · outbound

This paper cites Ale-bench: A benchmark for long-horizon objective-driven algorithm engineering.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Ale-bench: A benchmark for long-horizon objective-driven algorithm engineering

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.376050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6c3b84-5ab0-4514-9465-41eb81c205c5 · outbound

This paper cites Qwen3-Coder-Next Technical Report.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Qwen3-Coder-Next Technical Report

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.013414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a99526a-bf74-4095-8a51-4b4eb8ceb6b6 · outbound

This paper cites Deltaevolve: Accelerating scientific discovery through momentum-driven evolution.arXiv preprint arXiv:2602.02919,.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Deltaevolve: Accelerating scientific discovery through momentum-driven evolution.arXiv preprint arXiv:2602.02919,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.551317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c328d9e8-e157-4951-b19d-0384681ffe9e · outbound

This paper cites OpenAI o1 System Card.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning OpenAI o1 System Card

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.866319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4276ef4b-d744-4847-8398-4e57ee03d566 · outbound

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

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:28.178616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de564314-a21e-4d84-82d8-c59ab98209fc · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning Constitutional AI: Harmlessness from AI Feedback

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T06:17:27.935566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.