Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data | Paper Citation Record

Observation 3d982aff-524c-4a4b-99f9-06491df24d12 · outbound

This paper cites TTRL: Test-Time Reinforcement Learning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data TTRL: Test-Time Reinforcement Learning

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.011777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f7f0a398-e21b-4adc-858e-2091dc4b56c2 · outbound

This paper cites ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.052658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 43f1f110-ab36-4a96-bb50-dd20d000d334 · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.059877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a77039c5-391b-46f0-961b-c9bd3e6d4e0a · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data R-Zero: Self-Evolving Reasoning LLM from Zero Data

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T19:23:29.765778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 95ea86d6-6133-45e6-9987-8b5466e5ed5a · outbound

This paper cites One Token to Fool LLM-as-a-Judge.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data One Token to Fool LLM-as-a-Judge

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-12T02:08:19.458599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fdd4da0d-4987-4e9a-b13e-ced8e7368487 · outbound

This paper cites OpenAI o1 System Card.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data OpenAI o1 System Card

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.050328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 47a0b006-db2a-4212-8b40-51b8c559e048 · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.055017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6b320650-b316-425c-9ddd-a63262182404 · outbound

This paper cites Qwen3 Technical Report.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Qwen3 Technical Report

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.019262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5b18a2b9-e4fb-4e0e-ba7f-197c79a03bbb · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T08:21:05.971096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d67d51a4-c9e1-4ea0-94f3-2bcf7f5312e0 · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T12:12:09.004283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 52f3cb1b-099f-4c53-9e14-867cb07c84b5 · outbound

This paper cites Reinforcing General Reasoning without Verifiers.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Reinforcing General Reasoning without Verifiers

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.036290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b8b20a9b-7f99-42a0-9d14-1775e1bc2563 · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T12:31:34.026635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c5a719de-c496-4442-952c-34eb2b8251e0 · outbound

This paper cites Maximizing Confidence Alone Improves Reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Maximizing Confidence Alone Improves Reasoning

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.040925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 21d385bb-39f7-49c0-b23a-75d66eacf57b · outbound

This paper cites The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T15:58:33.819070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 98aa62d3-2ba4-46c1-a96c-2b8cb987701b · outbound

This paper cites Learning to Reason without External Rewards.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Learning to Reason without External Rewards

Reference 15

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 2026-08-04T06:34:03.388597+00:00.

Observation b03f0231-88d5-41b8-972d-ca08f6ba4319 · outbound

This paper cites Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.057418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d56d6ae-3ad8-4349-a497-dbd30086eec0 · outbound

This paper cites Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:02.038742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0ebb5673-a95c-46c8-b46b-c61a588a9abb · outbound

This paper cites s1: Simple test-time scaling.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data s1: Simple test-time scaling

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.024064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 696efccc-7a89-405e-80f4-a3c7a869dc1c · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.016993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9ea96b77-9e51-4be1-b951-b8c924bb42b2 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:23:58.476668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8ae0e32a-3386-4927-a0a5-ec71e8f0c24c · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.026279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e6d2d1b-a4e5-46e4-9faf-25570ad0a42e · outbound

This paper cites s1: Simple test-time scaling.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data s1: Simple test-time scaling

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.399505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 97b7fe68-7dfb-4165-bc4e-0cade0795304 · outbound

This paper cites e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.402466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f9113143-e73d-4457-9c01-23d025e5bb2b · outbound

This paper cites Can large reasoning models self-train?.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Can large reasoning models self-train?

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.968236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89cda544-1c8e-48f0-a479-3f16ac20cc81 · outbound

This paper cites First Conference on Language Modeling , year=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data First Conference on Language Modeling , year=

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.149853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4831cb6f-d040-423c-a5b9-d941ebdeb8cf · outbound

This paper cites Hugging Face repository , volume=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Hugging Face repository , volume=

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.156222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 98b3b3c6-30d8-4225-bfa1-75cf3791759a · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Measuring Mathematical Problem Solving With the MATH Dataset

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:00:39.484061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 55898f63-c9ab-42a1-9e93-f14d32339cfc · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.975383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 26110588-8257-45f7-bbd3-bde092241b05 · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data International conference on machine learning , pages=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.139626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c97915af-e7eb-4acc-b148-7d9ad74b52a5 · outbound

This paper cites Tent: Fully Test-time Adaptation by Entropy Minimization.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Tent: Fully Test-time Adaptation by Entropy Minimization

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T10:09:24.402331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 534b6c4f-b157-46aa-ba63-5fe0fa65c371 · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Advances in neural information processing systems , volume=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.137596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7ac4f40b-16d9-4972-8feb-a9c4b7a41e7a · outbound

This paper cites Workshop on challenges in representation learning, ICML , volume=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Workshop on challenges in representation learning, ICML , volume=

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.166341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6c1c20d2-4eb6-42f2-9452-72f79511353d · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data International conference on machine learning , pages=

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.168441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 63ddf2bd-59e8-48f4-a51e-3321c0340c5d · outbound

This paper cites Nature , volume=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Nature , volume=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.158224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 095e9a13-56fe-4811-9a1c-7278e980bc9c · outbound

This paper cites 1992 , publisher=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 1992 , publisher=

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.133855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 91a4765b-38ad-4bf6-b8e1-28fb4649bdc2 · outbound

This paper cites 2015 , publisher=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2015 , publisher=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.146122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation eec50442-9be8-410a-9192-680113fb5c04 · outbound

This paper cites Evolutionary computation , volume=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Evolutionary computation , volume=

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.162083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3150ed39-a429-4888-822e-2c036bfbba5e · outbound

This paper cites Frontiers in Robotics and AI , volume=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Frontiers in Robotics and AI , volume=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.170575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d85fd09c-20f7-485f-9cac-9bb1d58d1c65 · outbound

This paper cites Jointly Reinforcing Diversity and Quality in Language Model Generations.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Jointly Reinforcing Diversity and Quality in Language Model Generations

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.947611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 712dbd10-e8fa-4e8c-b391-6cdde66035f1 · outbound

This paper cites Modifying Large Language Model Post-Training for Diverse Creative Writing.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Modifying Large Language Model Post-Training for Diverse Creative Writing

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.965924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 039526f7-c65a-432c-a4db-ffbfe5e0f3b3 · outbound

This paper cites Supervising the search process produces reliable and generalizable information-seeking agents.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Supervising the search process produces reliable and generalizable information-seeking agents

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:02:48.394837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d41f4700-3287-4645-9187-33226ff86958 · outbound

This paper cites R1-RE: Cross-Domain Relation Extraction with RLVR.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data R1-RE: Cross-Domain Relation Extraction with RLVR

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.990762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c50ad9dd-2bad-4881-a5e8-43369204a2e7 · outbound

This paper cites CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.999728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4608f550-acd6-40c2-ad73-24abc60bcef4 · outbound

This paper cites Self-Rewarding Vision-Language Model via Reasoning Decomposition.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Self-Rewarding Vision-Language Model via Reasoning Decomposition

Reference 44

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:02.006979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4bf022af-6523-4e8d-b7b2-2929d433f2d5 · outbound

This paper cites Parallel-R1: Towards Parallel Thinking via Reinforcement Learning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:02.009207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0485d328-d6f1-41f6-99ea-6222fc70d86b · outbound

This paper cites Learning to Reason via Mixture-of-Thought for Logical Reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Learning to Reason via Mixture-of-Thought for Logical Reasoning

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.997503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f95d8c1f-8773-4da6-b3a5-dbcc2a60c164 · outbound

This paper cites arXiv preprint arXiv:2505.17312 , year=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data arXiv preprint arXiv:2505.17312 , year=

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.995170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 071fa43e-982e-4eb2-b78f-fd27e1edc040 · outbound

This paper cites In Proceedings of the 62nd Annual Meeting of the Association for Compu- tational Linguistics (Volume 3: System Demonstra- tions), Bangkok, Thailand.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data In Proceedings of the 62nd Annual Meeting of the Association for Compu- tational Linguistics (Volume 3: System Demonstra- tions), Bangkok, Thailand

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.992928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d5e49c82-93f5-4adb-b388-7b1d2a99e7c5 · outbound

This paper cites Defending Jailbreak Prompts via In-Context Adversarial Game.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Defending Jailbreak Prompts via In-Context Adversarial Game

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:02.001919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 698142b3-acf4-4bd0-8187-5ea823064abd · outbound

This paper cites 2023 , publisher =.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2023 , publisher =

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.135657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8e36973e-67df-41e7-9a97-302f3a39317d · outbound

This paper cites 2024 , eprint=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2024 , eprint=

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.144077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 678442dc-6f4e-4b81-9c71-cf18cc9545e6 · outbound

This paper cites 2024 , eprint=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2024 , eprint=

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.142084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 82b04643-3a14-492f-813f-e86bb6a40b19 · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Forty-first International Conference on Machine Learning , year=

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.152295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 45f50f34-9bc3-4bc8-bc40-73d74df433d9 · outbound

This paper cites Aligning Large Language Models by On-Policy Self-Judgment.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Aligning Large Language Models by On-Policy Self-Judgment

Reference 54

Resolution: verified exact; doi, observed 2026-05-10T05:36:01.404182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b657e844-1f88-4e90-bfe9-b4ed64598212 · outbound

This paper cites an unresolved cited work.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-21T20:14:21.154192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d77c955d-4b00-40ee-8a6e-d31116646c74 · outbound

This paper cites 2025 , eprint=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2025 , eprint=

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.164119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f71a7038-d81c-4929-b5a1-7fed1804b6cf · outbound

This paper cites 2024 , url=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2024 , url=

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.160158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2c8918ec-5cca-43ce-b873-f66263a5a20c · outbound

This paper cites 2025 , eprint=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2025 , eprint=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.131627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3d562eac-0960-4867-9192-5a117513b837 · outbound

This paper cites 2025 , eprint=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data 2025 , eprint=

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:14:21.148048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3837c19e-f352-4972-aee6-56285219ce18 · outbound

This paper cites Serl: Self-play reinforcement learning for large language models with limited data.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Serl: Self-play reinforcement learning for large language models with limited data

Reference 60

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.977673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 24083e58-3a7d-4795-ad66-57b4b709d172 · outbound

This paper cites Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.961406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 68a635f4-60e6-45b8-9935-fb20d3e069d7 · outbound

This paper cites arXiv preprint arXiv:2509.15194 , year =.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data arXiv preprint arXiv:2509.15194 , year =

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.949886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 07669db1-072f-490d-bc54-986566efa132 · outbound

This paper cites arXiv preprint arXiv:2509.23095 , year=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data arXiv preprint arXiv:2509.23095 , year=

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.988613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5162493c-3ae6-416d-8e69-bcf803ca90cc · outbound

This paper cites Clue: Non-parametric verification from experience via hidden-state clustering.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Clue: Non-parametric verification from experience via hidden-state clustering

Reference 64

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.972859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7d2189a3-1cd6-40b3-834c-fc70876c7e91 · outbound

This paper cites Can llms guide their own exploration? gradient-guided reinforcement learning for llm reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Can llms guide their own exploration? gradient-guided reinforcement learning for llm reasoning

Reference 65

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.986460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ac91009d-f39c-4271-9c98-335f9dd7d980 · outbound

This paper cites Exploring multi-temperature strategies for token-and rollout-level control in rlvr.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Exploring multi-temperature strategies for token-and rollout-level control in rlvr

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.970575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation de6189ef-5623-4637-a986-bdee79e7b202 · outbound

This paper cites V ogue: Guiding exploration with visual uncertainty improves multimodal reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data V ogue: Guiding exploration with visual uncertainty improves multimodal reasoning

Reference 67

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.942930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b8365cc-580e-4ddd-9fb8-b09be38c1ab5 · outbound

This paper cites Visplay: Self-evolving vision-language models from images.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Visplay: Self-evolving vision-language models from images

Reference 68

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.935863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation edfc3ae5-4955-4c93-bb1c-5879db03753e · outbound

This paper cites arXiv preprint arXiv:2510.02172 , year=.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data arXiv preprint arXiv:2510.02172 , year=

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.952217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation aa87b846-4536-486e-aa05-534c6f69aa0a · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:05:26.778195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 29bfc979-f3e0-4a74-bd01-18b712687633 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Proximal Policy Optimization Algorithms

Reference 71

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T05:36:01.940490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2c94ed64-a235-4ca7-afe5-59f43d3d5e7d · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 72

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.984213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0d3b114b-7072-4f2c-83fe-8eb9bab0386a · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T10:31:04.851073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 91e51ab2-e4e0-4a61-b9fc-5863ab8ade4b · outbound

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

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data The surprising effectiveness of negative reinforcement in llm reasoning.arXiv preprint arXiv:2506.01347

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.954519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 98630689-e10f-4b36-b5a8-5e003b457348 · outbound

This paper cites Save the good prefix: Precise error penalization via process-supervised rl to enhance llm reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Save the good prefix: Precise error penalization via process-supervised rl to enhance llm reasoning

Reference 75

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.956824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ae620dac-a917-4846-9c49-b721a7444220 · outbound

This paper cites Alignment Risks from Capability-Seeking RL Training.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Alignment Risks from Capability-Seeking RL Training

Reference 76

Resolution: metadata mismatch; arxiv_id, observed 2026-06-05T02:16:23.300865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 64d68eea-30f4-4754-b8df-bf4de29647c5 · outbound

This paper cites Stable and efficient single-rollout rl for multimodal reasoning.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data Stable and efficient single-rollout rl for multimodal reasoning

Reference 77

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:36:01.982078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers