Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond | Paper Citation Record

Observation 3a06483f-e30c-4c86-a0d8-fc1f430aa4c1 · inbound

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models cites this paper.

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 191

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T01:29:57.071592Z

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 61e3575d-57e1-43c4-ac9a-d246f320caf0 · inbound

Improving RL Exploration for LLM Reasoning through Retrospective Replay cites this paper.

Improving RL Exploration for LLM Reasoning through Retrospective Replay Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:28.847092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 616e83c4-3352-43ef-b983-289c2dbd6c2a · inbound

Learning to Reason under Off-Policy Guidance cites this paper.

Learning to Reason under Off-Policy Guidance Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T23:17:02.869340Z

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 03557996-dbda-41b0-8670-3f7c8f9d161f · inbound

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

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T10:39:31.300027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89e88595-6b82-4a51-ba4e-fabbdd4e0f50 · inbound

Reinforcement Learning for Reasoning in Large Language Models with One Training Example cites this paper.

Reinforcement Learning for Reasoning in Large Language Models with One Training Example Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T19:51:05.002577Z

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 9c66fe2a-5ebb-41b7-b8f2-e87660e5ff04 · inbound

100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models cites this paper.

100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 131

Resolution: unresolved; no resolver link, observed 2026-08-16T04:43:44.576915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce99a49-f25f-48f4-95fe-c7949ed87f8b · inbound

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models cites this paper.

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T23:56:46.331840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d6df71d-8774-429f-9625-23df6d8e680a · inbound

Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations cites this paper.

Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T21:07:08.171603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4767c9-cb2f-4298-bdf5-5277d918943c · inbound

MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities cites this paper.

MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:44.462106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c883251e-66ba-41a3-ba3f-4962c134865a · inbound

Towards A Generalist Code Embedding Model Based On Massive Data Synthesis cites this paper.

Towards A Generalist Code Embedding Model Based On Massive Data Synthesis Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:34:54.346546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51031af8-96fb-4a71-ae2a-093c23cca5ee · inbound

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning cites this paper.

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:06:35.469350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a891a60-d82e-4554-820c-e3eec9d5f64f · inbound

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN cites this paper.

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:05:18.720509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3a869c-772d-4d03-b820-8926f46311ae · inbound

QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning cites this paper.

QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:47:58.110674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6d38db-9d42-4123-b1f9-235377011f6b · inbound

Stable Reinforcement Learning for Efficient Reasoning cites this paper.

Stable Reinforcement Learning for Efficient Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:38:46.973811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58bcbb80-eed5-449a-9c08-cdb14c4ad7e0 · inbound

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models cites this paper.

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:31:12.891931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83f6548-a7f5-4fd5-aba7-4754a97c478f · inbound

MMATH: A Multilingual Benchmark for Mathematical Reasoning cites this paper.

MMATH: A Multilingual Benchmark for Mathematical Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:23:09.386204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 857e40f0-629c-4ec6-a05c-83cfacac4271 · inbound

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting cites this paper.

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:19.947222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1d4155d-0ead-46e9-a738-5be0cf0490c0 · inbound

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective cites this paper.

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 112

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:11.080617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28c8782f-2b2e-43bf-b38f-0383ac676e04 · inbound

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles cites this paper.

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:08.796570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eb165d9-c577-4497-85c8-12b25fff21a5 · inbound

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions cites this paper.

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:07:49.365734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a85ba105-22b8-4869-ad5a-b8688d9142cc · inbound

Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning cites this paper.

Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:41:30.443487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d906625e-03ee-4bc7-90cf-733794c7e472 · inbound

Skywork Open Reasoner 1 Technical Report cites this paper.

Skywork Open Reasoner 1 Technical Report Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T04:26:47.350497Z

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 6d56d6f1-1820-4fc9-865c-f168dcb42c1c · inbound

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? cites this paper.

Decomposing Elements of Problem Solving: What "Math" Does RL Teach? Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:27.038237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d1d414-ca7a-4e9a-8d5a-2ee63473299f · inbound

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models cites this paper.

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:21.956041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec882aa4-946f-4bb0-924e-0ca1319546e9 · inbound

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs cites this paper.

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:17:37.235199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 235ad0e0-a4d8-4234-93ea-98d1f2f340ca · inbound

Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning cites this paper.

Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:54:07.838570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf457c15-fa3a-4d33-a7ad-bcdc482e83be · inbound

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning cites this paper.

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:01:24.233618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39536fc5-73e8-4b6e-b543-381f67e043d0 · inbound

Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task cites this paper.

Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T01:05:26.848970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a6e346-aac4-4dea-a418-2222643eb1ae · inbound

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy cites this paper.

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:36.113617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c88e462-fd60-4c69-a1e3-02b0b28a2579 · inbound

Enhancing Large Language Models through Structured Reasoning cites this paper.

Enhancing Large Language Models through Structured Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T22:59:47.990084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cb3ee36-7012-4e15-b16c-47b1fc5031b4 · inbound

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning cites this paper.

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T18:39:18.971569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c17a0cd6-9280-4801-9636-f0b99cb58c8d · inbound

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants cites this paper.

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T20:46:22.631170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d0928f-6f77-40d6-9eaf-e34070df6e62 · inbound

Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model cites this paper.

Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T18:57:38.720506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c52c4c3-7204-4084-8ba8-a61935fa4f62 · inbound

A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning cites this paper.

A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:26:08.525387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4364aea-4370-4dbf-bd1e-802911a48418 · inbound

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey cites this paper.

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 200

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:17.847748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b60c03f1-14c4-4a95-a520-91ce8f4fccf3 · inbound

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once cites this paper.

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:31.692436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f940d917-eda9-44d6-8168-e3c54efb1326 · inbound

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

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T14:53:04.599526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba84593e-9ae9-4427-8d11-3e07adbfd0b4 · inbound

InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling cites this paper.

InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T22:34:23.988237Z

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 c5b6fc67-3e29-4c6a-bd9e-45e90dcbf817 · inbound

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models cites this paper.

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T16:19:53.921525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d205813b-567a-43ec-9793-c23f36ab7807 · inbound

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM cites this paper.

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T15:11:01.110314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08fe2101-9ae3-4671-9a47-74cd828efa0a · inbound

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework cites this paper.

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T05:45:04.041310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df28670-0e00-44f9-a3c3-8772a2db9d8a · inbound

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework cites this paper.

Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T05:45:04.085149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1c883b7-520d-4b4a-97f1-d8b690a827bc · inbound

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval cites this paper.

Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T23:23:41.779153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 400fda6c-c35b-4b51-92e0-b5081c768edb · inbound

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training cites this paper.

Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T13:31:24.978441Z

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 b7b7f24b-3eea-4265-9b27-09e63c6e8bb5 · inbound

The Signal is in the Steps: Local Scoring for Reasoning Data Selection cites this paper.

The Signal is in the Steps: Local Scoring for Reasoning Data Selection Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.172268Z

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 6eb96528-8a20-4626-b3e4-0e81d6459750 · inbound

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation cites this paper.

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 99

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:06:13.802986Z

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 15289bb2-e131-49f9-ae78-6e8beb41fd51 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T05:12:23.662328Z

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 be7e2720-b16e-4fdb-ae74-588e4da07b09 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T20:10:34.891829Z

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 a4abdab7-eff5-47e4-8935-3ee46b435881 · inbound

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning cites this paper.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.747822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14952ea-21c3-4e8c-8ef4-34e0280d2194 · inbound

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training cites this paper.

DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:48:50.926478Z

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 1bf0c8de-d4d5-449c-998f-c000e8621a0d · inbound

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models cites this paper.

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T14:10:13.173355Z

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 09a06dac-043b-4ecc-bfb4-0a1933af2e20 · inbound

Characterizing Model-Native Skills cites this paper.

Characterizing Model-Native Skills Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:06:19.521433Z

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 0e9be8f2-6c0b-4de7-98bb-6803cffdb2a4 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 159

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.755531Z

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 5a49ae54-1398-4a86-9a44-d95a03d6c9a1 · inbound

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards cites this paper.

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:46:28.509523Z

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 e229cccd-8685-440f-a136-6c54e5289bd3 · inbound

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs cites this paper.

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T02:46:18.839590Z

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 1d6efd00-eb3d-4326-8317-629164fefbbe · inbound

Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning cites this paper.

Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 59

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:15:02.865013Z

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 d4a5b6d9-9cbb-40e4-9b29-12e08523d53f · inbound

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance cites this paper.

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:21:09.548667Z

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 ae67e4f2-82f4-4c79-bc4f-db0a819cbd93 · inbound

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs cites this paper.

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T17:12:25.200187Z

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 221004fe-29e5-487f-8700-2e681c0208f9 · inbound

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning cites this paper.

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T04:27:36.717007Z

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 ec1f147d-143b-4586-bbec-816290c2e37b · inbound

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think cites this paper.

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:58:21.051491Z

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 1eafb797-f179-47da-97b1-418540031a12 · inbound

Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility cites this paper.

Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T14:49:03.983309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers