Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL | Paper Citation Record

Observation 22cd9d77-5bc3-43bf-9b6e-012dd366a55d · outbound

This paper cites L1: Controlling how long a reasoning model thinks with reinforcement learning, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL L1: Controlling how long a reasoning model thinks with reinforcement learning, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.155669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c9f5930-0553-42f5-9e99-0b969903eda9 · outbound

This paper cites Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.213407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c27a294e-71ce-4d0c-af54-188db47e8299 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Evaluating Large Language Models Trained on Code

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.231836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69fdc157-bbdc-465c-b495-18e1571d5675 · outbound

This paper cites JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.339231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e793c40-6723-4edc-a07b-443d5e24281c · outbound

This paper cites Empowering LLMs with Logical Reasoning: A Comprehensive Survey.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Empowering LLMs with Logical Reasoning: A Comprehensive Survey

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.386445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 212bd76f-6364-41ed-ac58-8ef82c2f2f98 · outbound

This paper cites Self- playing adversarial language game enhances llm reasoning.Advances in Neural Information Processing Systems, 37:126515–126543, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Self- playing adversarial language game enhances llm reasoning.Advances in Neural Information Processing Systems, 37:126515–126543, 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.796428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0e1d43cc-a800-41fa-9bd3-ba158b18055a · outbound

This paper cites Transformers as Soft Reasoners over Language.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Transformers as Soft Reasoners over Language

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.511121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a96dd2b-7f59-414c-b992-b6f92d214188 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.571433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09d5c820-15d6-4f1a-9671-70f7e1198aab · outbound

This paper cites Gemini 2.0 flash thinking, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Gemini 2.0 flash thinking, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.669140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5269d331-add4-4aea-a46d-b61819dccfba · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.728700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a8ec324-7c9d-4337-b5a0-2ec0abbe9e96 · outbound

This paper cites Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies.Transactions of the Association for Computational Linguistics, 9:346–361, 2021.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies.Transactions of the Association for Computational Linguistics, 9:346–361, 2021

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.798953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e546555a-3bc0-4ed5-b677-ec87a70695d5 · outbound

This paper cites LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.864107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd6ed91-71c9-4de7-b825-c40330044a9d · outbound

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

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:05.932027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d3bab2-ec8e-4b06-b5ea-c4ff44d58900 · outbound

This paper cites FOLIO: Natural Language Reasoning with First-Order Logic.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL FOLIO: Natural Language Reasoning with First-Order Logic

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.003231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a19a564f-598b-4599-a236-031e91b38bdf · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Measuring mathematical problem solving with the math dataset

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.068109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 355d0c2c-b29a-472a-a57c-407d9fa9959e · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.155144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18da2e70-102c-4c7f-8c81-4fd3f7fa4496 · outbound

This paper cites Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.221502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6442c8e8-9681-4416-9224-33767f2bbff7 · outbound

This paper cites Boardgameqa: A dataset for natural language reasoning with contradictory information.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Boardgameqa: A dataset for natural language reasoning with contradictory information

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.734162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2922c9ec-3339-4875-bddc-725e62d6c14e · outbound

This paper cites Buy 4 REINFORCE samples, get a baseline for free! In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop, New Orleans, Louisiana, United States, May 6, 2019.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Buy 4 REINFORCE samples, get a baseline for free! In Deep Reinforcement Learning Meets Structured Prediction, ICLR 2019 Workshop, New Orleans, Louisiana, United States, May 6, 2019

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.704465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ee6cc1d8-bbdd-4b9b-9e66-7843aa934929 · outbound

This paper cites Chain of code: Reasoning with a language model-augmented code emulator.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Chain of code: Reasoning with a language model-augmented code emulator

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.678037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 03c8f9e5-1a42-40d5-b2da-16e5218e12b3 · outbound

This paper cites CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.261278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a7f6c22-c1a8-4074-a35e-e00a8c6b8587 · outbound

This paper cites Limr: Less is more for rl scaling, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Limr: Less is more for rl scaling, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.266810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c61012-3a83-4b03-9eea-bf583e5e64ee · outbound

This paper cites From system 1 to system 2: A survey of reasoning large language models, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL From system 1 to system 2: A survey of reasoning large language models, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.644307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 29969c6a-139c-4e09-a049-55ed9bb828c8 · outbound

This paper cites ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.276239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8423668f-70ee-447b-833a-9dee553df8a4 · outbound

This paper cites Natural language inference in context-investigating contextual reasoning over long texts.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Natural language inference in context-investigating contextual reasoning over long texts

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.628502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3e1a4b64-531c-4654-89b3-9a8337c56d83 · outbound

This paper cites Logiqa 2.0—an improved dataset for logical reasoning in natural language understanding.IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2947–2962, 2023.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Logiqa 2.0—an improved dataset for logical reasoning in natural language understanding.IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2947–2962, 2023

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.610533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 95a44259-4307-4cc3-8ac1-b9ac02df23cf · outbound

This paper cites 大模型逻辑推理研究综述 (survey on logical reasoning of large pre- trained language models).

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL 大模型逻辑推理研究综述 (survey on logical reasoning of large pre- trained language models)

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.593555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 273438f4-5775-49f5-885a-3fef33514fc5 · outbound

This paper cites LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.296264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5f3609-3501-456a-943d-3574cbc9e3f6 · outbound

This paper cites Understanding r1-zero-like training: A critical perspective, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Understanding r1-zero-like training: A critical perspective, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.302217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4789af-807a-449b-9d8d-a0c69a8ccd72 · outbound

This paper cites Reasoning with large language models for medical question answering.Journal of the American Medical Informatics Association, 31(9):1964–1975, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Reasoning with large language models for medical question answering.Journal of the American Medical Informatics Association, 31(9):1964–1975, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.560070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e5db605-f610-426a-a1aa-ccd084413474 · outbound

This paper cites Improve mathematical reasoning in language models by automated process supervision, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Improve mathematical reasoning in language models by automated process supervision, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.543417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8ca36034-17c8-4859-8c4b-7a18a21a1959 · outbound

This paper cites Exploring the limit of outcome reward for learning mathematical reasoning, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Exploring the limit of outcome reward for learning mathematical reasoning, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.320941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64b2246-ff11-42ec-b052-3c2b371c4d6d · outbound

This paper cites Real: Efficient rlhf training of large language models with parameter reallocation.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Real: Efficient rlhf training of large language models with parameter reallocation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.325245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89658dd5-f79b-4562-8d19-88c8603d5be1 · outbound

This paper cites Enhancing reasoning capabilities of llms via principled synthetic logic corpus.Advances in Neural Information Processing Systems, 37:73572–73604, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Enhancing reasoning capabilities of llms via principled synthetic logic corpus.Advances in Neural Information Processing Systems, 37:73572–73604, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.489665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9965ee69-3d72-4e05-9625-12449474ce55 · outbound

This paper cites Advanced semantics for commonsense knowledge extraction.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Advanced semantics for commonsense knowledge extraction

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.465259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a2abe552-b684-461c-8ee6-e02b32a85bb3 · outbound

This paper cites Learning to reason with llms, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Learning to reason with llms, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.340441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a124621e-0d8f-45cd-878f-6db8f00f9a15 · outbound

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

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.345622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36668151-2c8f-4385-8f61-4c85f13e2149 · outbound

This paper cites Making reasoning matter: Measuring and improving faithfulness of chain-of-thought reasoning.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Making reasoning matter: Measuring and improving faithfulness of chain-of-thought reasoning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.421265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c84e8efc-0eb1-408a-b7e6-609ab6f1ef72 · outbound

This paper cites Qwen2.5 technical report, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Qwen2.5 technical report, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.355048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc4097e-25ec-4b96-a47e-faf186ca7e4d · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Qwq-32b: Embracing the power of reinforcement learning, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.361130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8703507-c9af-4c01-8e63-1957d0e91145 · outbound

This paper cites Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.366029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f0895b-9acb-461c-9d78-6c8844fc20b8 · outbound

This paper cites Testing the general deductive reasoning capacity of large language models using ood examples.Advances in Neural Information Processing Systems, 36:3083–3105, 2023.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Testing the general deductive reasoning capacity of large language models using ood examples.Advances in Neural Information Processing Systems, 36:3083–3105, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.381247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 53e22eda-0e18-4252-9fd6-6c8b7321b991 · outbound

This paper cites High-dimensional continuous control using generalized advantage estimation, 2018.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL High-dimensional continuous control using generalized advantage estimation, 2018

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.375876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4665d72d-0ab1-45b7-9720-a7522d293317 · outbound

This paper cites Proximal policy optimization algorithms, 2017.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Proximal policy optimization algorithms, 2017

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.380438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76bf7573-9660-4de6-b51b-193c6c08f8cc · outbound

This paper cites Automatic solutions of logic puzzles.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Automatic solutions of logic puzzles

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.332435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e2a07ee8-ad48-43d5-bdb8-7c983b3c3e7d · outbound

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

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.390455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3877bd5-b1fc-4b05-8349-1711b53a8446 · outbound

This paper cites Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.395257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8531279f-7ae6-4beb-933a-c0eb75e3c785 · outbound

This paper cites To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.402593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8b7f272-204d-465c-a1aa-7444d57cf1f9 · outbound

This paper cites MIT press Cambridge, 1998.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL MIT press Cambridge, 1998

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.408266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f4937f-ea0b-4334-a053-bd4aaf3d7510 · outbound

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

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.413231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad3b24a-8875-480f-9a86-f853f97c303b · outbound

This paper cites Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:42:06.625878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c0cf8e43-d49e-4adf-a9be-78609e07433b · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.302087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d9c6894b-eabb-43b7-9ca1-1543ab1a513c · outbound

This paper cites Measuring multimodal mathematical reasoning with math-vision dataset.Advances in Neural Information Processing Systems, 37:95095–95169, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Measuring multimodal mathematical reasoning with math-vision dataset.Advances in Neural Information Processing Systems, 37:95095–95169, 2024

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.429383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 543ede4a-f228-40e4-8e54-4343af2b16e0 · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.263273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 71bd38f1-573f-4554-bff1-6b107809ad40 · outbound

This paper cites Legalreasoner: A multi-stage framework for legal judgment prediction via large language models and knowledge integration.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Legalreasoner: A multi-stage framework for legal judgment prediction via large language models and knowledge integration

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.244773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8ce955bc-2e1d-48be-a995-f1f6c09e22ea · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.445735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2e16b8-680b-44d5-8e29-414d7bb94455 · outbound

This paper cites On memorization of large language models in logical reasoning.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL On memorization of large language models in logical reasoning

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.216188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 36449521-a3f2-453d-a8b9-af3ee859ceb8 · outbound

This paper cites Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Logic-rl: Unleashing llm reasoning with rule-based reinforcement learning, 2025

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.455832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94806828-92e3-4d58-bd00-648bf406b4d7 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.460031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b6e9fb-a1bd-4f56-8651-e9a10cae643d · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Dapo: An open-source llm reinforcement learning system at scale, 2025

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.464464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652cb997-1e1d-4751-bc58-5e4b95ddbf04 · outbound

This paper cites Lawllm: Intelligent legal system with legal reasoning and verifiable retrieval.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Lawllm: Intelligent legal system with legal reasoning and verifiable retrieval

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.174320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a2e9bfbd-2315-4212-ae65-7a9fcd6943c1 · outbound

This paper cites Rest-mcts*: Llm self-training via process reward guided tree search, 2024.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Rest-mcts*: Llm self-training via process reward guided tree search, 2024

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.474025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4404c5fd-2fa1-423a-a3b1-419b3d1c9fc1 · outbound

This paper cites ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.478842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb0d3350-691f-4d83-82e6-406ba2ede228 · outbound

This paper cites R1-reward: Training multimodal reward model through stable reinforcement learning, 2025.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL R1-reward: Training multimodal reward model through stable reinforcement learning, 2025

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.136777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 921924ed-5215-4ebe-ba12-99a806a60fa3 · outbound

This paper cites AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T04:42:06.489294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8179a4a-a3d1-4047-9b5b-e87933e7816b · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.115497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 031ed804-4040-4d9e-b669-bb1e4e812f50 · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.090966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0c848a07-871c-470a-92bc-4a2048ff9b50 · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.069307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 63fdc848-2390-47ce-b156-8f6f6ed1cfdf · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.050266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e0dcc09d-4cc0-470b-9de8-7480d9989c85 · outbound

This paper cites an unresolved cited work.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:42:07.031013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5ceff70f-fa52-4110-b4aa-9ba3b33e5eb8 · outbound

This paper cites Alice studies.

Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL Alice studies

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:42:07.011688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers