Paper Citation Record · LEDGER

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

As of 6 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 1 inbound Pith citation observation for arXiv:2605.00380.

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

pith.paper-citation-record.v1
2605.00380 v2

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T02:07:21.806345Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T21:54:44.271066Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-04T21:54:44.689229Z

Reference resolution

68 of 68 outbound references displayed

verified exact6
verified fuzzy27
unresolved8
parse uncertain1
malformed identifier0
metadata mismatch26

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 471bdb82-b65c-402a-98e1-3de2ac1190ef · outbound

This paper cites Langley , title =.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Langley , title =

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:16:17.337713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 546a4df3-dc4a-4b22-b01f-11c5e2f40e23 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:16:17.342271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d096e0b7-8402-4e5e-bb7e-352bd1147f78 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 3

Resolution: parse uncertain; raw_fallback, observed 2026-05-14T14:16:17.330303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4da24c35-06fb-4158-8db0-3f9a315c748b · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:16:17.332843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b967ab9-2ee1-4df0-bac4-e57c71f87615 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:16:17.344241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4803c362-8cb1-402d-8537-518eeb78cfe1 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:16:17.335377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 406212ef-e759-450e-a834-e38342b55c0a · outbound

This paper cites Newell and P.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Newell and P

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:16:17.327742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e1bd28a7-41d1-46ee-b70e-dd8f09a8d416 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:16:17.339890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 23fcf05c-f0ed-4744-926e-53855e604130 · outbound

This paper cites The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.033665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 880d5381-d9cc-4161-950c-81ae076f5f4e · outbound

This paper cites The Surprising Effectiveness of Negative Reinforcement in.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The Surprising Effectiveness of Negative Reinforcement in

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.035306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9282e36f-e792-444c-a8f1-b454bf2d2a72 · outbound

This paper cites 2025 , eprint=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2025 , eprint=

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.030238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 952cbc23-2de4-49f2-8a03-2a4550e4d2b7 · outbound

This paper cites The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.028665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a9f59b6-9f0b-411a-842f-70542e8f564c · outbound

This paper cites Do We Really Need All Those Dimensions? An Intrinsic Evaluation Framework for Compressed Embeddings.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Do We Really Need All Those Dimensions? An Intrinsic Evaluation Framework for Compressed Embeddings

Reference 13

Resolution: verified exact; doi, observed 2026-05-11T02:10:52.878362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57af6f8b-5697-4d51-b7c9-d910f59de4ff · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:11:04.031831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c9b9538-fd4e-4a39-9708-f02b89daa0d0 · outbound

This paper cites How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.608612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fb620dd3-b316-484c-9a96-df6b99fb768b · outbound

This paper cites SC20: International Conference for High Performance Computing, Networking, Storage and Analysis , pages=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning SC20: International Conference for High Performance Computing, Networking, Storage and Analysis , pages=

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.037134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d9c4c92-432d-4edf-a220-859ba6ee7e03 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Advances in neural information processing systems , volume=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.041049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 55ba95a8-e18a-4715-af88-7c0abf63dbc1 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Forty-second International Conference on Machine Learning , year=

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.039179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5adda6ef-1d25-4a5d-830e-8e2c27d3dee5 · outbound

This paper cites Layer Normalization.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Layer Normalization

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.660430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a9a2743d-76a0-4a1c-a585-caeb0e3e4063 · outbound

This paper cites 2013 , publisher=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2013 , publisher=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:16:17.323594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b47d64d0-5500-4649-8639-d9475e7b60e6 · outbound

This paper cites 2012 , publisher=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2012 , publisher=

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.023176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5c5f73ef-355f-4e69-981f-055e1109037d · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Group-in-Group Policy Optimization for LLM Agent Training

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:15:09.492454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 502ff5c2-6737-426d-b756-4871a14cb9a7 · outbound

This paper cites Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:56.612400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 61eae873-89f3-4b89-8134-0b1b5bd8e10f · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.527005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cfbfb84a-302b-46eb-ab12-bdf53d39204c · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.487618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5ef8e421-23e5-4f7f-910d-c73b75fc891b · outbound

This paper cites arXiv preprint arXiv:2509.15207 , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning arXiv preprint arXiv:2509.15207 , year=

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:56.625674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e3470641-c74e-463a-b4ab-f68fe91a9841 · outbound

This paper cites The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:56.547823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a789e726-9a07-42a8-a130-b84c4795a9bc · outbound

This paper cites Proceedings of the Twentieth European Conference on Computer Systems , pages=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Proceedings of the Twentieth European Conference on Computer Systems , pages=

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.025041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e0e4642-05a5-4796-a31b-cc271a856477 · outbound

This paper cites The eleventh international conference on learning representations , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The eleventh international conference on learning representations , year=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.016699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0bf572a1-7a80-4ba8-991f-542737855d8b · outbound

This paper cites GPT-4o System Card.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning GPT-4o System Card

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.688441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation acfc92db-99d4-4235-b2d4-287104cf5a5e · outbound

This paper cites 2017 , eprint=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2017 , eprint=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.014824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bc9a82e9-b86d-4558-afa0-f073776677e3 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.589250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b2e24013-a5aa-46d8-8fed-112e11d49622 · outbound

This paper cites 2016 , eprint=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2016 , eprint=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.018322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f326481c-385c-4b6d-bce3-657f849182d0 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:11:04.019859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c388450a-fc2b-4452-b222-870cf0b2aecd · outbound

This paper cites 2023 , howpublished=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2023 , howpublished=

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.009231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e47e96c3-14cc-4ed8-962f-d48d67b988b0 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning The Twelfth International Conference on Learning Representations , year=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.006026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a89baf4e-26eb-4081-8727-b3c3a7386eca · outbound

This paper cites Solving Quantitative Reasoning Problems with Language Models , volume =.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Solving Quantitative Reasoning Problems with Language Models , volume =

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.004234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4cf893df-5431-429f-8196-76fc6a99ddce · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T08:38:21.105975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4147c05d-ae60-4ba5-9d3e-38e7bab3a220 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.572533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 284d3897-1ef7-402a-8df1-e990dbe55012 · outbound

This paper cites Hugging Face repository , howpublished =.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Hugging Face repository , howpublished =

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.007708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d7d630a9-7b5e-49d8-a25a-2259477db3c9 · outbound

This paper cites 2021 , eprint=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2021 , eprint=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.011105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e972309a-a452-4238-8e36-6b3dab9f0e2e · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Advances in Neural Information Processing Systems , volume=

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.021557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 245dd79f-19e2-4f08-8a3d-7cd7e80cdfcb · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 43

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:39:15.970362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d2efa496-1a1c-403c-88be-3e9ed309c279 · outbound

This paper cites an unresolved cited work.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-05-14T14:11:04.026652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a203321-8085-45f3-bcb4-c465ea4f78d1 · outbound

This paper cites 2025 , eprint=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2025 , eprint=

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:03.998682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ef6e31e4-9e4d-4251-8137-34fcac0e28dc · outbound

This paper cites Qwen3 Technical Report.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Qwen3 Technical Report

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.499161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 40050088-539c-4c1b-a497-c5fe56084642 · outbound

This paper cites InThe Twelfth Inter- national Conference on Learning Representations.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning InThe Twelfth Inter- national Conference on Learning Representations

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.495465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 241c99f0-3248-48d3-9161-04e3d76b4885 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Advances in Neural Information Processing Systems , volume=

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.002613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8aedebd1-aba0-43a3-88c1-02f6e87acf0c · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning ToolRL: Reward is All Tool Learning Needs

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T00:26:48.594660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fae9b3ce-9444-4c51-916d-d9f31c3d8476 · outbound

This paper cites On grpo collapse in search-r1: The lazy likelihood- displacement death spiral.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning On grpo collapse in search-r1: The lazy likelihood- displacement death spiral

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.558114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 974941f5-c810-405a-a532-08dd6be20681 · outbound

This paper cites arXiv preprint arXiv:2508.03772 , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning arXiv preprint arXiv:2508.03772 , year=

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:56.568629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a72436e-d0b4-42cb-8d71-39d42638d9f5 · outbound

This paper cites 2nd AI for Math Workshop@ ICML 2025 , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning 2nd AI for Math Workshop@ ICML 2025 , year=

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:03.997138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f0ca4aaf-90d5-4706-bdf6-b147accde66f · outbound

This paper cites Token-level Direct Preference Optimization.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Token-level Direct Preference Optimization

Reference 53

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.600639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78c5861d-4769-40ff-af89-31b2727ac214 · outbound

This paper cites Surrogate signals from format and length: Reinforcement learning for solving mathematical problems without ground truth answers.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Surrogate signals from format and length: Reinforcement learning for solving mathematical problems without ground truth answers

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.629247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f37e4fc4-c1e1-499b-b715-821b0df128b9 · outbound

This paper cites Learning to Reason without External Rewards.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Learning to Reason without External Rewards

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T21:16:57.297836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f0af7455-69d4-43f4-a332-c2eef49e8601 · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Spurious Rewards: Rethinking Training Signals in RLVR

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T13:37:51.161107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2effd303-1372-46d9-91c5-f44aafb19f77 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 57

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.670222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 970e2a00-9a0a-4ef2-a527-75ccb0bbab77 · outbound

This paper cites Beyond the Sampled Token: Preserving Candidate Support in RLVR.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Beyond the Sampled Token: Preserving Candidate Support in RLVR

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-06-19T17:09:49.354484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 62a36ce3-ff9e-40dd-8908-3e040a63392a · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 59

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.653228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 51162d63-f47d-4295-aad7-d13027ce7f2f · outbound

This paper cites Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.520021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ba339bc3-a0a6-439b-8147-b70473565199 · outbound

This paper cites DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Reference 61

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.677053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5c712013-bb5f-41fa-9ad7-1ab6b67256b3 · outbound

This paper cites From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR

Reference 62

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T03:55:56.685011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 42724834-59a7-4969-a8d7-4a2f898c3f30 · outbound

This paper cites Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Reference 63

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T03:55:56.507385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 461bf939-b0d7-4603-9146-f56ea80e2fb3 · outbound

This paper cites Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Reference 64

Resolution: metadata mismatch; arxiv_id, observed 2026-06-11T02:08:32.357336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cefedd71-81d0-496d-993d-1865e9e04c10 · outbound

This paper cites arXiv preprint arXiv:2511.16231 , year=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning arXiv preprint arXiv:2511.16231 , year=

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:56.645213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5e7a2117-5866-4393-b713-60a3e750c308 · outbound

This paper cites Proceedings of the 31st International Conference on Computational Linguistics , pages=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Proceedings of the 31st International Conference on Computational Linguistics , pages=

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:03.995438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fb342ba8-0328-4d25-86f1-b30f71632a71 · outbound

This paper cites Transactions of the association for computational linguistics , volume=.

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Transactions of the association for computational linguistics , volume=

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.000792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ab1f043-7895-44d4-9dd2-73f1bb734a20 · outbound

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

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning Advances in neural information processing systems , volume=

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T14:11:04.013107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation beb7572e-2aad-4fb6-9fb2-415e538b6b4d · inbound

Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning cites this paper.

Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Reference 62

Resolution: metadata mismatch; local_arxiv, observed 2026-08-04T21:54:44.693998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.