SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs | Paper Citation Record

Observation 68c54f4a-d5d9-41dc-9fc1-ea37fa6c5f7f · outbound

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

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.838386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e540975b-3755-44ed-adb4-eee6f0b51777 · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.842437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9172b590-a96a-47f1-b0b3-e0985bd86175 · outbound

This paper cites Notion Blog , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Notion Blog , year=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.845618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 009d592c-9a2c-474c-8709-cd8e53b922cf · outbound

This paper cites Notion Blog , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Notion Blog , year=

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.848882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f17af8-7ccf-4e48-938b-cbb778f2c6c8 · outbound

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

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.851939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da74fc9-5c31-4edd-9266-4f6cc37f89a6 · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.855511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d050213-bfa5-414b-887d-78aa2ef677e4 · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.859031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 270372db-3e7e-49ea-83bc-6355322e8c5a · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.862030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7986a9-0f38-4aed-8526-47d14e2458cb · outbound

This paper cites RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.865455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 475e09fa-8e71-49f3-842f-6c38be11a240 · outbound

This paper cites How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.868703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3b5cc92-d26b-49ef-b432-57eb6e5f6e2f · outbound

This paper cites 2025 , school=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , school=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.871996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96fabbca-42e0-4c5a-9bf6-ebb1ae74bcb1 · outbound

This paper cites Journal of Machine Learning Research , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Journal of Machine Learning Research , volume=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.874964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0a38f5c-106b-452c-8fb9-329dc3164034 · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Forty-first International Conference on Machine Learning , year=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.877955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 711a6dea-54c6-46d2-8ce5-15955619d8de · outbound

This paper cites 2024 , journal =.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2024 , journal =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.880970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b468e741-8353-48b7-be51-fbe16876cb46 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.883937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ac2037-c10d-42e2-a7b3-704cf0f240a7 · outbound

This paper cites arXiv preprint arXiv:2505.11711 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2505.11711 , year=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.887173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f534c9f5-c07d-4188-a3af-c49375af7665 · outbound

This paper cites OpenAI o1 System Card.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs OpenAI o1 System Card

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.889992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45ef809b-2384-4458-82f2-a4e384dee59d · outbound

This paper cites arXiv preprint arXiv:2510.00553 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2510.00553 , year=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.893127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 234113de-6718-4f5b-9b69-bb659ea26ca7 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Advances in Neural Information Processing Systems , volume=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.896219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11c81482-b16b-42cc-b5cf-e67d9efc2be1 · outbound

This paper cites RL's Razor: Why Online Reinforcement Learning Forgets Less.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs RL's Razor: Why Online Reinforcement Learning Forgets Less

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.899233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71923b72-fb19-4cd1-aa22-2eb690f3c77a · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.902409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c23186-5130-4f8c-af90-2984a31afaf1 · outbound

This paper cites 2013 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2013 , eprint=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.905310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71140767-a30f-4303-83f9-ea0281e40b19 · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.960024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e8335b22-ae85-4996-9a33-057bfcda0d32 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Advances in Neural Information Processing Systems , volume=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.911800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19efbbe8-f5ee-48fc-945b-4efdc4e3cc93 · outbound

This paper cites Finding Skill Neurons in Pre-trained Transformer-based Language Models.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Finding Skill Neurons in Pre-trained Transformer-based Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.914427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feda317e-f4f1-4c84-b724-c765eae22b4d · outbound

This paper cites RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.917563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70b8ca03-76d2-45bd-b9b4-a146edd8dffa · outbound

This paper cites an unresolved cited work.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.920696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b4f520d-f52f-43b1-bb3c-9ce02f0269af · outbound

This paper cites Group Sequence Policy Optimization.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Group Sequence Policy Optimization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.923464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f87fda-c97a-430d-b473-60434b3e0f85 · outbound

This paper cites Advances in neural information processing systems , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Advances in neural information processing systems , volume=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.926486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ae546c-595f-4e1e-a732-6e2679834658 · outbound

This paper cites RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.929359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee3b23d-47c9-4d05-9d9a-702c441e85fe · outbound

This paper cites an unresolved cited work.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-08T00:51:25.941163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation da7ea94d-8785-4431-b5ad-f5af98effe21 · outbound

This paper cites arXiv preprint arXiv:2508.11408 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2508.11408 , year=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.934982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66463944-db0e-4f81-8a74-1a8135b269ac · outbound

This paper cites SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.937566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 764de3c9-cf85-4936-97b8-d44c84de81e5 · outbound

This paper cites arXiv preprint arXiv:2507.14783 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2507.14783 , year=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.940643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5880889f-ada6-4589-9536-bf1cd6f24903 · outbound

This paper cites an unresolved cited work.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-08T00:51:25.933261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f249f6e5-1491-4e43-a410-13aca663e1a2 · outbound

This paper cites Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T00:51:25.419952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d23f51b-9412-441b-8f52-eee04f5eb2d9 · outbound

This paper cites 2024 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2024 , eprint=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.948610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745e9d7f-2acd-4bb7-806e-e4293d9babc8 · outbound

This paper cites arXiv e-prints , pages=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv e-prints , pages=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.951367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e4dbc1-7e97-4fd0-bd8f-3b58a041cdb2 · outbound

This paper cites Advances in neural information processing systems , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Advances in neural information processing systems , volume=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.954073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e190c4f2-4725-41c1-a6ff-9c092fa92250 · outbound

This paper cites When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.956984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f05ed9c-ec62-4b30-9b7f-37ca7a45157a · outbound

This paper cites International Conference on Machine Learning , pages=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs International Conference on Machine Learning , pages=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.959992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a093eb83-067c-4172-a1a6-286c9091e8d5 · outbound

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

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Fine-Tuning Language Models from Human Preferences

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.962646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9057cc-3348-44d9-ba0d-a8fb64914c59 · outbound

This paper cites arXiv preprint arXiv:2510.23451 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2510.23451 , year=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.965740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f808ad9-c7ac-4b19-b4f4-ff9731543c33 · outbound

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

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.968486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13da6049-b004-45c3-8c9a-93018bb1f1c4 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Kimi K2: Open Agentic Intelligence

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.971347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274a4626-4b3f-42e1-81e8-c4211dc99651 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Finetuned Language Models Are Zero-Shot Learners

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.974293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64744e12-324e-44ba-9f40-65a2bb6ec4be · outbound

This paper cites Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.977379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfa8e593-2751-444f-86c4-dd747e1b95de · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.980199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c809825-2207-4248-b986-1e64ec13d22c · outbound

This paper cites arXiv preprint arXiv:2510.19178 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2510.19178 , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.983165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2022819-1246-49c2-a20d-d370e0f34043 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.985898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71867253-54ed-464c-97bb-90248c9e3e5a · outbound

This paper cites RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.989053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a246913d-eed8-4d9d-95b8-df2f8c98ef22 · outbound

This paper cites 2025 , url =.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , url =

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.991738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6296a290-b359-4605-b99c-cf693850f86e · outbound

This paper cites 2025 , url =.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , url =

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.903509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6420f249-30c8-4e0e-ac34-9ca34ea51e94 · outbound

This paper cites Qwen3 Technical Report.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Qwen3 Technical Report

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.997044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76f66b0a-8911-4d14-9334-55a992341558 · outbound

This paper cites DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:24.999803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df3ba475-cc66-4b8a-9ffb-891e6bf26385 · outbound

This paper cites 2024 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2024 , eprint=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.002728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c329527-5d4b-4c46-a22d-af845ac75ecb · outbound

This paper cites 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) , pages=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE) , pages=

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.892013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9361a7d4-2b63-4187-9363-1051be6d3c82 · outbound

This paper cites Let's Verify Step by Step.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Let's Verify Step by Step

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.008147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a48c120-3fd5-4099-a059-871c5e3a22a5 · outbound

This paper cites 2021 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2021 , eprint=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.011091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efdddd95-982f-4daf-9c61-14879811b92e · outbound

This paper cites 2023 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2023 , eprint=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.014006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daab03e9-76d4-4b8a-a62f-0f4be1d86bee · outbound

This paper cites 2024 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2024 , eprint=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.017043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6c23ea-e248-4b6e-bd5c-d74225384034 · outbound

This paper cites 2021 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2021 , eprint=

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.019902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c45c70-a3fa-41a4-b4bc-aa80d8848f8f · outbound

This paper cites 2023 , version =.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2023 , version =

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.869420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f778c1ea-d242-4c17-a6bb-f44267396d80 · outbound

This paper cites Proximal Policy Optimization Algorithms.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Proximal Policy Optimization Algorithms

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.025149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f8860d8-de94-47b4-ac83-0f576c4dc1db · outbound

This paper cites SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.027810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c7924ec-49e9-472d-8b0d-ef809e3e2859 · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.030741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d846356e-fef5-4e2c-bb81-dcab8bd5d115 · outbound

This paper cites 2021 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2021 , eprint=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.033447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95efbe3e-738e-4301-8e88-cf35352831ed · outbound

This paper cites 2018 , publisher=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2018 , publisher=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.036133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a82567e2-1149-4f66-9bd1-8d6940c54fab · outbound

This paper cites arXiv preprint arXiv:2511.08567 , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs arXiv preprint arXiv:2511.08567 , year=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.038958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 992b03f0-173e-4f22-af7c-5828a9d78df8 · outbound

This paper cites 2023 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2023 , eprint=

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.041478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2ae80be-b48c-4a30-8693-dbf3e39bd428 · outbound

This paper cites Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.044392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff86dea-41c1-47b1-9ea2-89aaca1fd3c3 · outbound

This paper cites Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.047158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e66d5eb6-190b-4889-a7df-0d3c10249ede · outbound

This paper cites The Fourteenth International Conference on Learning Representations , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs The Fourteenth International Conference on Learning Representations , year=

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.845486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 89566f01-e99a-4fe2-aa09-d5807c6082a6 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.837858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 975416e0-961b-4e25-9587-d5bfc019080c · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Forty-second International Conference on Machine Learning , year=

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.829860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 47e5bb23-9f6d-4127-b083-cd1a1cf26d76 · outbound

This paper cites International conference on machine learning , pages=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs International conference on machine learning , pages=

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.058003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 556712b3-94f1-45aa-b5fb-6909f09cefe5 · outbound

This paper cites Editing Models with Task Arithmetic.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Editing Models with Task Arithmetic

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.060648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8209ebf-a8f4-45fe-9f2e-50e7deaccfbf · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Forty-first International Conference on Machine Learning , year=

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.063688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ffd96e5-6234-4689-84bd-408099ee5923 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Advances in Neural Information Processing Systems , volume=

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.066306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1912973d-21a4-4e46-8168-a210dc0e8dfc · outbound

This paper cites Dataless Knowledge Fusion by Merging Weights of Language Models.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Dataless Knowledge Fusion by Merging Weights of Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-08T00:51:25.068937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caf44552-0cef-4061-bad3-19aaea3ae23a · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.810348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ddd4fee7-4ce1-4dc2-a313-a8d2c9ee7221 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.802733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39cc38b0-c77e-4038-accc-df121c4630b7 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.794796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6b056ef3-3e89-4599-a46b-8c5d3df82a23 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.786970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 82ccedf0-eeb8-4730-a59e-b833c30585a2 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.778971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 678625fb-776c-4013-88ad-7afa773708d4 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.770980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation abf48d9c-71d8-4055-b9e7-41899d946b6f · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.762900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 10ddd987-57c6-4940-a2b7-328d30167c99 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.754873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22fc5538-5170-4c1d-b216-5e3ca146df99 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.747135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7478ca43-fb12-4840-ba87-a003ba3c8dff · outbound

This paper cites 2025 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2025 , eprint=

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.739308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f4b5e2d6-d10d-4199-969d-945f04036517 · outbound

This paper cites 2026 , eprint=.

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs 2026 , eprint=

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:51:25.730046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers