Paper Citation Record · LEDGER

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

As of 6 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2607.22529.

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

pith.paper-citation-record.v1
2607.22529 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T04:28:49.464315Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0aa6daad-b7c5-4289-8cdf-61e05fa1dbdc · outbound

This paper cites Ultraif: Advancing instruction following from the wild.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Ultraif: Advancing instruction following from the wild

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:44.927193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a535cdee-e078-49be-b9bc-64cd775d6504 · outbound

This paper cites SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.144472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82e338f-656d-468f-ac41-3df830a9e4b3 · outbound

This paper cites I want to plan a dinner for my friends this weekend in Portland. We’re looking for a nice Italian place that doesn’t cost more than $30 per person.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills I want to plan a dinner for my friends this weekend in Portland. We’re looking for a nice Italian place that doesn’t cost more than $30 per person

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.404490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8b6ba3-07ec-41c1-8899-32f9e7845c05 · outbound

This paper cites From self-evolving synthetic data to verifiable-reward rl: Post-training multi-turn interactive tool-using agents.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills From self-evolving synthetic data to verifiable-reward rl: Post-training multi-turn interactive tool-using agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.458502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba3d182-65cb-4f0c-a6a5-429435763b84 · outbound

This paper cites RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.552110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2efc86d2-a72e-4ffe-a41c-9dce29985975 · outbound

This paper cites Gems: Agent-native multimodal generation with memory and skills.arXiv preprint arXiv:2603.28088,.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Gems: Agent-native multimodal generation with memory and skills.arXiv preprint arXiv:2603.28088,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.639596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f755cd-4170-43dd-ac7a-4442881dbc90 · outbound

This paper cites R-Zero: Self-Evolving Reasoning LLM from Zero Data.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills R-Zero: Self-Evolving Reasoning LLM from Zero Data

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.732564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1187567d-5631-46c9-8bae-981a4ff62159 · outbound

This paper cites Bowen Jiang, Taiwei Shi, Ryo Kamoi, Yuan Yuan, Camillo J Taylor, Longqi Yang, Pei Zhou, and Sihao Chen.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Bowen Jiang, Taiwei Shi, Ryo Kamoi, Yuan Yuan, Camillo J Taylor, Longqi Yang, Pei Zhou, and Sihao Chen

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.841654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64db138e-10e3-4c85-9ef0-86e5ca864eb2 · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.954722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434e22b1-81ff-4212-a799-f31a0f7c68af · outbound

This paper cites R-diverse: Mitigating diversity illusion in self-play llm training.arXiv preprint arXiv:2602.13103, 2026a.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills R-diverse: Mitigating diversity illusion in self-play llm training.arXiv preprint arXiv:2602.13103, 2026a

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.184528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde93b8d-d7c9-49f3-b762-451245bfa63e · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.307495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e96f8b1d-10c6-4b08-bdf5-ad7be70090cf · outbound

This paper cites Agent skills: A data-driven analysis of claude skills for extending large language model functionality.arXiv preprint arXiv:2602.08004,.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Agent skills: A data-driven analysis of claude skills for extending large language model functionality.arXiv preprint arXiv:2602.08004,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.439202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f867384-7fb6-4afc-a086-205fb99b4c50 · outbound

This paper cites Ministral 3.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Ministral 3

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.545451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9521f4d7-2342-4664-8f4d-1a88f3503ef3 · outbound

This paper cites SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.657137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0bef9a0-5c8e-4d82-9306-3bcf9227c841 · outbound

This paper cites Search Self-play: Pushing the Frontier of Agent Capability without Supervision.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Search Self-play: Pushing the Frontier of Agent Capability without Supervision

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.810522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d173e1cc-a592-4c26-a775-d1566ce09ab8 · outbound

This paper cites SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.952475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d74f686-e46e-4e04-80d0-371b74be435c · outbound

This paper cites Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.064528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91c76fc2-5099-44d7-848c-2a4df08b4823 · outbound

This paper cites Better alignment with instruction back-and-forth translation.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Better alignment with instruction back-and-forth translation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.217091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88c5bb2-7079-4a47-a693-2a4933a77eea · outbound

This paper cites Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.335859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15964e59-f02a-42c4-85d8-0bad85c80133 · outbound

This paper cites Large Language Models Can Self-Improve At Web Agent Tasks.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Large Language Models Can Self-Improve At Web Agent Tasks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.436292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f32634f-2afc-489b-866f-bf837084d20a · outbound

This paper cites Infobench: Evaluating instruction following ability in large language models.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Infobench: Evaluating instruction following ability in large language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.552765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f8aee4f-fa73-4196-8831-2197fb3ef672 · outbound

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

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.668921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef2ee6f-18ea-4836-bf27-e9b421aa3821 · outbound

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

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.878934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d9e1a79-94e1-4133-bf5f-48e89bcb0001 · outbound

This paper cites SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.022530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01050069-831c-4d3c-bc99-413d35f3e41b · outbound

This paper cites A Survey on Self-Evolution of Large Language Models.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills A Survey on Self-Evolution of Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.253415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ede134-3d16-42ad-ada1-d4ac6ac62866 · outbound

This paper cites Code-a1: Adversarial evolving of code llm and test llm via reinforcement learning.arXiv preprint arXiv:2603.15611, 2026a.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Code-a1: Adversarial evolving of code llm and test llm via reinforcement learning.arXiv preprint arXiv:2603.15611, 2026a

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.304531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36cfbba1-346e-4c22-a86c-f7d320e895ff · outbound

This paper cites Toward Training Superintelligent Software Agents through Self-Play SWE-RL.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Toward Training Superintelligent Software Agents through Self-Play SWE-RL

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.430179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0351b3c-df92-4b77-b934-d95962ece4e1 · outbound

This paper cites Propose, solve, verify: Self-play through formal verification.arXiv preprint arXiv:2512.18160,.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Propose, solve, verify: Self-play through formal verification.arXiv preprint arXiv:2512.18160,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.564168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c223b5c-34cd-47a6-9283-f3f904b07b23 · outbound

This paper cites Wizardlm: Empowering large pre-trained language models to follow complex instructions.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Wizardlm: Empowering large pre-trained language models to follow complex instructions

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.732010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d81a9a8-731e-4485-b7f3-514beb42fd7a · outbound

This paper cites OpenSkill: Open-World Self-Evolution for LLM Agents.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills OpenSkill: Open-World Self-Evolution for LLM Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.825254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f323bd6-937c-496f-bcba-61d5d76ad2fc · outbound

This paper cites Qwen3 Technical Report.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Qwen3 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.911778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e14d102-216a-41ad-a1c2-4695e8cd40b1 · outbound

This paper cites CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.960183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35acc60b-73d9-4046-8363-e7e252ca2fd6 · outbound

This paper cites Learning to Reason without External Rewards.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Learning to Reason without External Rewards

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.009194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f798bf16-0179-4e87-afc2-09e4b6e5797d · outbound

This paper cites SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.067525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cf073f6-9c81-4cd5-8578-a9cf77f80205 · outbound

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

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Instruction-Following Evaluation for Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.133550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7c0064-307a-4281-b5c6-0dc9d1a4f021 · outbound

This paper cites Webarena: A realistic web environment for building autonomous agents.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Webarena: A realistic web environment for building autonomous agents

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.194675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation defb9909-59c5-48be-a39f-08b213d06789 · outbound

This paper cites SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.274654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36b44770-e84a-47f1-98f5-5dafee72db1f · outbound

This paper cites project updates.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills project updates

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.329638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2175526-f46e-4dc3-90fa-b52d953befb4 · outbound

This paper cites schedule a meeting.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills schedule a meeting

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:49.464315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d419ccf-b96f-4864-bf73-32ada2d1824f · outbound

This paper cites EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:48.135993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b32beb6-35e5-4885-bc22-505a1fea3841 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:47.805036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ae9a1c-8fde-48eb-a40e-cb7097003ffc · outbound

This paper cites Language self-play for data-free training.arXiv preprint arXiv:2509.07414,.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Language self-play for data-free training.arXiv preprint arXiv:2509.07414,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:46.086644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 064ca75f-2f59-4c0e-88c8-753332ffd3d5 · outbound

This paper cites SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.255280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd69018d-9cdf-4f1b-b65d-2d2cc94df016 · outbound

This paper cites Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.019999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232f5c1d-59d6-4eaa-a412-8853239a5168 · outbound

This paper cites Self- play with execution feedback: Improving instruction-following capabilities of large language models.

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Self- play with execution feedback: Improving instruction-following capabilities of large language models

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T04:28:45.367391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.