LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts | Paper Citation Record

Observation 0f0a37e7-5dd7-44d0-9cc5-833ec769b190 · outbound

This paper cites Tina: Tiny Reasoning Models via LoRA.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Tina: Tiny Reasoning Models via LoRA

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.596043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e50381b-8495-4fee-8f2e-e3fd4db4bd9d · outbound

This paper cites arXiv preprint arXiv:2506.07527 , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts arXiv preprint arXiv:2506.07527 , year =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.668707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5db1f480-06ca-44b2-9dda-d0bf5756f576 · outbound

This paper cites Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.739458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2134da-3e3b-48b4-a765-437228c091dd · outbound

This paper cites arXiv preprint arXiv:2603.23871 , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts arXiv preprint arXiv:2603.23871 , year =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.804128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dfaeff7-2e76-4d4a-aa44-f287a72a3801 · outbound

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

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.868005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d577706-0b84-40fa-a279-107c03bb98fe · outbound

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

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:55.933165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc8666ee-9c78-461b-8061-8a6766171add · outbound

This paper cites Proximal Policy Optimization Algorithms.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Proximal Policy Optimization Algorithms

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.048240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a609134-d9db-4a73-af55-5bd7091cdc5c · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts LoRA: Low-Rank Adaptation of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.118443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86296fed-8a99-430f-88c2-a5cd2006e074 · outbound

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

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.176653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72fd49f8-e1e1-40ae-961e-20159b36095b · outbound

This paper cites DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.250910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aab03436-8a35-4566-ac31-d16a11b3dfbd · outbound

This paper cites Neural Information Processing Systems , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Neural Information Processing Systems , year =

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.314615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ab55e9-f415-4fd1-b962-59834df789e2 · outbound

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

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts International Conference on Learning Representations , year =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.378939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec18f94-a102-46f5-b48b-f740d5d70b10 · outbound

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

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts International Conference on Learning Representations , year =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.405734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a322e6-43e8-4c23-82bf-bb4f8775ecf0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Evaluating Large Language Models Trained on Code

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.470597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4495b5d9-cd5e-4933-b98b-7ca4606f0f15 · outbound

This paper cites Understanding.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.627338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 994c961a-99d7-4a9e-8378-21d7cd9ceb46 · outbound

This paper cites Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.693276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec73280-de7c-4484-9790-8ab6114ce01c · outbound

This paper cites 2026 , note =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2026 , note =

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.748724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a28dfa1e-ec7f-4daf-9161-39c79fab2afe · outbound

This paper cites arXiv preprint arXiv:2602.03143 , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts arXiv preprint arXiv:2602.03143 , year =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.816872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44774df2-16d2-449b-ad90-d338b1fb4e2f · outbound

This paper cites arXiv preprint arXiv:2604.00698 , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts arXiv preprint arXiv:2604.00698 , year =

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.878791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36266788-8891-4384-989c-d055085520ef · outbound

This paper cites Nudging the Boundaries of.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Nudging the Boundaries of

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:56.929960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96aa2ad7-4baf-4a65-8b3c-8389cd68567b · outbound

This paper cites 2025 , url =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2025 , url =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.003113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44efb7f-7866-4efa-bc4f-8b03875d0489 · outbound

This paper cites Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.015362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8002cd4-72a9-4660-8c2a-48c472e5bda0 · outbound

This paper cites 2025 , note =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2025 , note =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.021388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation febe30bb-ebf8-499c-800f-b25b943b293e · outbound

This paper cites 2026 , url =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2026 , url =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.026690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57629963-d642-40e3-bd50-702dc651009b · outbound

This paper cites and Jeon, Myeongho and Vu, Kim and Lai, Viet and Yang, Eunho , booktitle =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts and Jeon, Myeongho and Vu, Kim and Lai, Viet and Yang, Eunho , booktitle =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.032975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2383483f-77f7-4825-baa7-7a6489d929fa · outbound

This paper cites Don't Waste Mistakes: Leveraging Negative.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Don't Waste Mistakes: Leveraging Negative

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.038231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8371c59e-caf1-4dd7-8099-7f61e6cc8e03 · outbound

This paper cites 2026 , url =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2026 , url =

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.043917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867c3a41-5dea-48b4-90af-b8473fb3ac32 · outbound

This paper cites Learning-Zone Energy: Online Data Selection for Efficient.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Learning-Zone Energy: Online Data Selection for Efficient

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.049520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f2ddb01-de73-45dc-9642-0555e779ac66 · outbound

This paper cites Advances in Neural Information Processing Systems (.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Advances in Neural Information Processing Systems (

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.055572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b379e5-4de0-40a8-8c4a-8349696534d3 · outbound

This paper cites , booktitle =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts , booktitle =

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.060474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d9fe803-993c-41df-8b11-df54279391a9 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.065296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d3af5fb-81d3-4b49-8cb9-37789a57780c · outbound

This paper cites Reinforced Self-Training (.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Reinforced Self-Training (

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.071439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08879f88-e5ab-4680-8ffd-5309f37c4f48 · outbound

This paper cites Transactions on Machine Learning Research (.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Transactions on Machine Learning Research (

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.076222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce414c73-cf32-4c85-863a-2c5b02663067 · outbound

This paper cites Learn Hard Problems During.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Learn Hard Problems During

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.081170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e738eace-afee-47af-b3bc-b827e9956532 · outbound

This paper cites Robotics: Science and Systems (.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Robotics: Science and Systems (

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.086165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a5c976-f6cc-4178-aab0-586be606dc7a · outbound

This paper cites Advances in Neural Information Processing Systems (.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Advances in Neural Information Processing Systems (

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.091777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7f6980c-6371-495c-8c23-170743bfbe5d · outbound

This paper cites 2024 , note =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts 2024 , note =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.098425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5355ae5-d164-4197-8444-a5fd2b447f52 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Process Reinforcement through Implicit Rewards

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.103793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c9b497d-6b11-4188-b807-6a05c317ccd3 · outbound

This paper cites Efficient.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts Efficient

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.109916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0005115-698a-4cb8-bfa5-8e2ecc2e6567 · outbound

This paper cites International Conference on Machine Learning (ICML) , year =.

LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts International Conference on Machine Learning (ICML) , year =

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T01:28:57.123789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers