Paper Citation Record · LEDGER

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

As of 20 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 8 inbound Pith citation observations for arXiv:2505.11827.

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

pith.paper-citation-record.v1
2505.11827 v2

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:52:27.870796Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T20:23:59.391394Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T05:13:58.683288Z

Reference resolution

67 of 67 outbound references displayed

verified exact0
verified fuzzy7
unresolved59
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8e1dba22-f59a-42c0-bded-9c6f5d4bdb45 · outbound

This paper cites Learning to reason with llms.https://openai.com/index/learnin g-to-reason-with-llms/, 2024.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Learning to reason with llms.https://openai.com/index/learnin g-to-reason-with-llms/, 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.848459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e3748f0a-bde4-4d82-9f1e-060c14ae6806 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.639546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ac5935-22e6-42db-bdd7-5244f26444ca · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.644098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8f5373e-6d3d-4440-aa18-d314bbfad2f4 · outbound

This paper cites Introducing openai o1.https://openai.com/o1/, 2024.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Introducing openai o1.https://openai.com/o1/, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.647305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5cfc72-4287-4bcf-b555-5bd139d88c34 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.650871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fc4f2a-5bb0-4c20-bbf8-728a31a1a393 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.658521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b157013-fddc-4f84-9a4a-d1d1a375fd2b · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Gpqa: A graduate-level google-proof q&a benchmark

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.661450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a969319-8f2c-4325-9f57-8bbdac892614 · outbound

This paper cites The Impact of Reasoning Step Length on Large Language Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning The Impact of Reasoning Step Length on Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.664401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31fb7393-e939-4dbd-883a-4a878431eb63 · outbound

This paper cites Compressed Chain of Thought: Efficient Reasoning Through Dense Representations.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Compressed Chain of Thought: Efficient Reasoning Through Dense Representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.668099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25566f2e-0ee5-481c-a220-65747c2038a9 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Chain of Draft: Thinking Faster by Writing Less

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.671402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f4ef41c-fd30-4d41-9521-3e5d656545dd · outbound

This paper cites Overthink: Slowdown attacks on reasoning llms.arXiv e-prints, pages arXiv–2502, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Overthink: Slowdown attacks on reasoning llms.arXiv e-prints, pages arXiv–2502, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.822616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f0b5292a-738b-42b2-8c1a-a7f835de7063 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Token-Budget-Aware LLM Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.677819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b5bd5a4-9389-41e0-8ac2-56201a426bb3 · outbound

This paper cites Qwen3 technical report.https://github.com/QwenLM/Qwen3, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Qwen3 technical report.https://github.com/QwenLM/Qwen3, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.812993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e908915e-3fa1-4ce7-bbad-d0357e9bf397 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.685481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afa4310-dec1-4d01-a029-46e5ef2e3580 · outbound

This paper cites The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.688704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850607b7-d2b6-4c07-9949-2d3547d9615a · outbound

This paper cites C3ot: Generating shorter chain-of-thought without compromising effectiveness.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning C3ot: Generating shorter chain-of-thought without compromising effectiveness

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.692641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a84781a2-bf34-4873-9b11-d09c97742971 · outbound

This paper cites Dyve: Thinking Fast and Slow for Dynamic Process Verification.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Dyve: Thinking Fast and Slow for Dynamic Process Verification

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.695931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b09a1b-1fa5-48db-bfb0-559bfab9b492 · outbound

This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.699687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ff6136-31eb-4de6-ad29-1eb61a5528b7 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.704228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b20208bc-ead9-42da-a680-41fd3a7d5472 · outbound

This paper cites Online and offline reinforcement learning by planning with a learned model.Advances in Neural Information Processing Systems, 34:27580–27591, 2021.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Online and offline reinforcement learning by planning with a learned model.Advances in Neural Information Processing Systems, 34:27580–27591, 2021

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.798121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 985d6bf2-2a28-42a4-89c4-d0e65b46cbf0 · outbound

This paper cites Dast: Difficulty-adaptive slow-thinking for large reasoning models.arXiv preprint arXiv:2503.04472, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Dast: Difficulty-adaptive slow-thinking for large reasoning models.arXiv preprint arXiv:2503.04472, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.710089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edff6d17-bcb0-4dca-a2d2-fb029ef536d1 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36:53728–53741, 2023.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36:53728–53741, 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.713053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1be2436-b5c5-4c4e-9c5c-4d84596db1d3 · outbound

This paper cites Training language models to reason efficiently.arXiv preprint arXiv:2502.04463, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Training language models to reason efficiently.arXiv preprint arXiv:2502.04463, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.715892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5986889f-1302-414a-ade3-7b66de653f7e · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.719429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fadac48b-a9aa-41f3-8f7c-219aef7d1526 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.723462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ba20099-7780-449f-806b-b73a8ac4f8cd · outbound

This paper cites ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.726983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a40e80ad-2282-480d-8db0-e3cef605a3e0 · outbound

This paper cites ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.730903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765784a6-0dc0-4231-97e6-dbc6a8b6d504 · outbound

This paper cites Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching.arXiv preprint arXiv:2503.05179, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching.arXiv preprint arXiv:2503.05179, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.733962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e477dc24-4d10-4354-9d19-a314b218a1cd · outbound

This paper cites Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.736820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 502911ea-43e2-4047-8336-6c8b367e5000 · outbound

This paper cites Multi-turn Reinforcement Learning from Preference Human Feedback.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Multi-turn Reinforcement Learning from Preference Human Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.740448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ce1d644-c834-4bdc-b210-d44b430e6f02 · outbound

This paper cites SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.744073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31efee27-1b1e-43ca-9bb5-bd2bc54ce65f · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.747468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed3566b4-85de-4e3d-af50-03f48fbbac4f · outbound

This paper cites Understanding Aha Moments: from External Observations to Internal Mechanisms.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Understanding Aha Moments: from External Observations to Internal Mechanisms

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.751482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b0b348-7b01-4df4-930f-59b4a7fc3cb2 · outbound

This paper cites A mean value theorem in geometry of numbers.Annals of Mathematics, 46(2):340– 347, 1945.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning A mean value theorem in geometry of numbers.Annals of Mathematics, 46(2):340– 347, 1945

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.782955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fca55852-c6bc-4c30-9094-c5cea4f1f8cc · outbound

This paper cites Full Parameter Fine-tuning for Large Language Models with Limited Resources.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Full Parameter Fine-tuning for Large Language Models with Limited Resources

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.758311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abb78ab0-561d-4ed0-9d23-7cb9bea99dd7 · outbound

This paper cites Group robust preference optimization in reward-free rlhf.Advances in Neural Information Processing Systems, 37:37100–37137, 2024.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Group robust preference optimization in reward-free rlhf.Advances in Neural Information Processing Systems, 37:37100–37137, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.762022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27b61284-ff46-400b-9713-7e947da215eb · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.765050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520ef70c-bec0-4975-9246-5a424b32a98e · outbound

This paper cites The Llama 3 Herd of Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning The Llama 3 Herd of Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.767942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 618aa3ef-6adc-4710-ada4-e97572a50cee · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.771802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a23f9d3-94b7-438e-99dc-eb19b18c3fdb · outbound

This paper cites Aime problems and solutions.https://artofproblemsolving.com/wiki/ index.php, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Aime problems and solutions.https://artofproblemsolving.com/wiki/ index.php, 2025

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.766318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dee9d6e8-c74d-48fe-9103-8c312fea37f6 · outbound

This paper cites American mathematics competitions.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning American mathematics competitions

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:52:28.755841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 655a4ab2-74dc-46d4-90db-9e1180f84fa4 · outbound

This paper cites Openmathinstruct-1: A 1.8 million math instruction tuning dataset.Advances in Neural Information Processing Systems, 37:34737–34774, 2024.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Openmathinstruct-1: A 1.8 million math instruction tuning dataset.Advances in Neural Information Processing Systems, 37:34737–34774, 2024

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.782764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fe5c724-7d25-45a1-8fee-a2e28a7f8623 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.786159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e802468b-9b07-4702-be93-1e2a8ccf773c · outbound

This paper cites ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.789583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94b89a96-f547-4572-aef0-f4973a882a20 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.792807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14214f1d-8fa2-486a-afaf-38116cfeba96 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.796197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574eb0f7-8cee-4c95-a05d-36c3acc8843f · outbound

This paper cites Reinforcement learning: A survey.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Reinforcement learning: A survey

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.799680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1a0a3a-9cd3-4480-9401-8af1e76688a9 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.803424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f35f72-7e74-4449-ab0f-915e23473538 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.806763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395f7013-2ea5-4df3-b813-2eeebbd629cf · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.Advances in Neural Information Processing Systems, 37:124198–124235, 2024.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Simpo: Simple preference optimization with a reference-free reward.Advances in Neural Information Processing Systems, 37:124198–124235, 2024

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.809993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184f5881-91fc-48fc-b1d4-f8fefd141967 · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.812991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1742f3de-8276-4f9c-be08-59518fb6d091 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning ToolRL: Reward is All Tool Learning Needs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.816985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f1c130-c44c-48b9-871e-a2aeea3c6cb7 · outbound

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

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.820470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 776fd629-9eb6-44f0-b51e-a5c6e1992dcb · outbound

This paper cites How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.824350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7a02d69-6fa8-43ed-8bc6-e8f34317e1b0 · outbound

This paper cites Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.827471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d3519c-2fec-46b2-87f7-24724493797f · outbound

This paper cites When More is Less: Understanding Chain-of-Thought Length in LLMs.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning When More is Less: Understanding Chain-of-Thought Length in LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.831037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd76593-d63d-450b-9f2d-31865105f96f · outbound

This paper cites Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.835260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9c5322d-43cd-4113-a0bf-1b7508694eb1 · outbound

This paper cites Towards thinking-optimal scaling of test-time compute for llm reasoning.arXiv preprint arXiv:2502.18080, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Towards thinking-optimal scaling of test-time compute for llm reasoning.arXiv preprint arXiv:2502.18080, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.838341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b39363-d6ff-43eb-87ea-418ba1404c9a · outbound

This paper cites CoT-Valve: Length-Compressible Chain-of-Thought Tuning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.842063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c433c0-bc47-4fd9-a618-9f009a0397f4 · outbound

This paper cites CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.845785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 109476f8-8def-475d-9ffb-b1d75da5e7c9 · outbound

This paper cites Self-Training Elicits Concise Reasoning in Large Language Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Self-Training Elicits Concise Reasoning in Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.849593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cca3f5df-7e8b-40bf-bd8f-0156febd332b · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.853828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a821dc8e-b968-4b71-a921-b53b2085702b · outbound

This paper cites Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.856904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 816da435-fdff-4de7-b8de-eb6a2dda2275 · outbound

This paper cites Lightthinker: Thinking step-by-step compression.arXiv preprint arXiv:2502.15589, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Lightthinker: Thinking step-by-step compression.arXiv preprint arXiv:2502.15589, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.860411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f1b8f7-0988-4533-ad2e-a02915e295c3 · outbound

This paper cites Inftythink: Breaking the length limits of long-context reasoning in large language models.arXiv preprint arXiv:2503.06692, 2025.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Inftythink: Breaking the length limits of long-context reasoning in large language models.arXiv preprint arXiv:2503.06692, 2025

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.864055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9e3d244-2771-4265-97ee-a3044ef22b02 · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.866978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f0da7bb-d5dc-4627-a65f-8716e3b0cd23 · outbound

This paper cites Given that47−1≡51 (mod 97) , find 28−1 (mod 97), as a residue modulo 97. (Give a number between 0 and 96, inclusive.).

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning Given that47−1≡51 (mod 97) , find 28−1 (mod 97), as a residue modulo 97. (Give a number between 0 and 96, inclusive.)

Reference 68

Resolution: malformed identifier; no resolver link, observed 2026-08-15T20:52:27.870796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c49ac434-a5a7-4105-9e34-bfe3de753a62 · inbound

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

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 134

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:29:56.635307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 54dd50c3-df24-42f5-b8f8-ec4744002cf9 · inbound

MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs cites this paper.

MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T20:23:59.391394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a4e6cdf-4396-4f8f-b656-829fb196fad7 · inbound

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

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 140

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:17.525716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8a8e0be-0c63-4936-a4fb-ca7f1444b804 · inbound

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization cites this paper.

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T00:13:27.574670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58067f36-3c1b-4b8f-9e29-0b375f8f95b4 · inbound

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

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 216

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.128184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2e4eb112-31b7-4a18-8ae7-d9998e1a7ce3 · inbound

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective cites this paper.

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-21T05:13:58.685140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 59fc4700-df1c-4469-b7c4-14d4160378d4 · inbound

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning cites this paper.

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:07:01.503753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d5fba01-f539-49c5-bb77-0ff2e354f696 · inbound

Chained Recursive Language Models for Multi-Iteration Reasoning cites this paper.

Chained Recursive Language Models for Multi-Iteration Reasoning Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:18.195206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.