Paper Citation Record · LEDGER

Think Only When You Need with Large Hybrid-Reasoning Models

As of 10 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 17 inbound Pith citation observations for arXiv:2505.14631.

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

pith.paper-citation-record.v1
2505.14631 v2

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:37:09.232525Z

measured 73 of 73 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:49:36.120187Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T06:15:23.470485Z

Reference resolution

56 of 56 outbound references displayed

verified exact0
verified fuzzy14
unresolved40
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f0d258e0-2497-4a57-ab5a-d0cb54663bce · outbound

This paper cites Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs.

Think Only When You Need with Large Hybrid-Reasoning Models Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:12.893144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16d6e4c3-1b4f-49a3-871e-49c12aa119cb · outbound

This paper cites Aime 2024, 2024.

Think Only When You Need with Large Hybrid-Reasoning Models Aime 2024, 2024

Reference 2

Resolution: parse uncertain; no resolver link, observed 2026-08-07T15:37:02.243996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7339d900-16c0-4e30-a86b-a880b24cbc53 · outbound

This paper cites Claude 3.7 sonnet and claude code.

Think Only When You Need with Large Hybrid-Reasoning Models Claude 3.7 sonnet and claude code

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:12.670595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2749490d-dcd0-46c4-8f29-7f8eab4048ed · outbound

This paper cites Program Synthesis with Large Language Models.

Think Only When You Need with Large Hybrid-Reasoning Models Program Synthesis with Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:02.474112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d10e9891-aca8-488f-be3f-d2e7216e192a · outbound

This paper cites Le, Christopher Ré, and Azalia Mirhoseini.

Think Only When You Need with Large Hybrid-Reasoning Models Le, Christopher Ré, and Azalia Mirhoseini

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:12.418759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d66c9a4-7d13-44b5-9abc-b3511e2ff18c · outbound

This paper cites Kcts: Knowledge-constrained tree search decoding with token-level hallucination detection, 2023.

Think Only When You Need with Large Hybrid-Reasoning Models Kcts: Knowledge-constrained tree search decoding with token-level hallucination detection, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:12.156197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc61526b-c2b1-4815-9b98-fd9221a49629 · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3.

Think Only When You Need with Large Hybrid-Reasoning Models R1-v: Reinforcing super generalization ability in vision-language models with less than \ 3

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:02.820708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc6923d-6884-4494-9691-cc77d2758eaa · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:02.982109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfefc874-29c1-462c-962b-82f402d608d2 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.084426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e5e1f7-ff45-47d4-a941-253c91ad1d54 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Think Only When You Need with Large Hybrid-Reasoning Models Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.194688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574c23be-a34a-4f9a-9237-11a0993ea8b6 · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.308859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 576b7f90-f7fe-4b8d-86c2-b46c553ce4a0 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

Think Only When You Need with Large Hybrid-Reasoning Models Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.477338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a0a6d19-3472-43b9-b256-9bd39e8d0040 · outbound

This paper cites Gemini 2.5 flash.

Think Only When You Need with Large Hybrid-Reasoning Models Gemini 2.5 flash

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:11.928092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 828d9768-a2e2-45a2-bcde-c74dffe2e801 · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.740911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35d7d021-0049-4a9e-91e5-aeb30c502b1f · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Think Only When You Need with Large Hybrid-Reasoning Models Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.889816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c71ef2fb-77fc-42ee-9c0b-f1a2f3602df9 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024.

Think Only When You Need with Large Hybrid-Reasoning Models Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.993628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71bb26c6-2df2-42da-9920-c64c728256cd · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:04.130902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e50156-ea22-4684-b6f8-2050133d8fd0 · outbound

This paper cites Rewarding chatbots for real-world engagement with millions of users, 2023.

Think Only When You Need with Large Hybrid-Reasoning Models Rewarding chatbots for real-world engagement with millions of users, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:11.652175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 92fce269-ba75-46b3-9b09-3b33a9d0ca99 · outbound

This paper cites FastText.zip: Compressing text classification models.

Think Only When You Need with Large Hybrid-Reasoning Models FastText.zip: Compressing text classification models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:04.391801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 445c261e-a4aa-4db5-9e8e-0af7b39bb338 · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:04.484693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73afd0e7-392d-4e94-876d-761860fe5d30 · outbound

This paper cites o pf, Yannic Kilcher, Dimitri Von R \.

Think Only When You Need with Large Hybrid-Reasoning Models o pf, Yannic Kilcher, Dimitri Von R \

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:11.375604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e3225f1e-9f0b-40d6-80a5-97ad8d566f60 · outbound

This paper cites From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline.

Think Only When You Need with Large Hybrid-Reasoning Models From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:04.744210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52bdb838-558a-4c5e-9a22-d2380370e451 · outbound

This paper cites Don't throw away your value model! generating more preferable text with value-guided monte-carlo tree search decoding, 2024.

Think Only When You Need with Large Hybrid-Reasoning Models Don't throw away your value model! generating more preferable text with value-guided monte-carlo tree search decoding, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:11.198576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c077f6d-67ad-43d5-bb8a-c968717ef7be · outbound

This paper cites A simple model of inference scaling laws, 2024.

Think Only When You Need with Large Hybrid-Reasoning Models A simple model of inference scaling laws, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:05.028806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7534cc9-8241-4aa0-ae45-6aaf9d149475 · outbound

This paper cites Let's Verify Step by Step.

Think Only When You Need with Large Hybrid-Reasoning Models Let's Verify Step by Step

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:05.168215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d849a0e2-fa79-4d83-ad47-402e1a9f7dea · outbound

This paper cites Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D.

Think Only When You Need with Large Hybrid-Reasoning Models Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:11.081533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1bc9e7d-950c-42b6-b786-68d5824ea077 · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:05.462460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48f9134-afa7-41dd-8531-81feb49ec946 · outbound

This paper cites Video-T1: Test-Time Scaling for Video Generation.

Think Only When You Need with Large Hybrid-Reasoning Models Video-T1: Test-Time Scaling for Video Generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:05.609652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98699e6-9a86-48e7-a4ad-1c808cfa95d3 · outbound

This paper cites Evaluating Language Models for Efficient Code Generation.

Think Only When You Need with Large Hybrid-Reasoning Models Evaluating Language Models for Efficient Code Generation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:05.745275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e152a90-affe-4a9e-a99d-ec3c89bff1e9 · outbound

This paper cites Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation.

Think Only When You Need with Large Hybrid-Reasoning Models Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:10.771774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b0c159a4-e73f-446e-a49e-152e5bc61f69 · outbound

This paper cites AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset.

Think Only When You Need with Large Hybrid-Reasoning Models AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.016932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f95b16-9cae-4c54-8e70-64a4e58f0faf · outbound

This paper cites Synthetic-1: Two million collaboratively generated reasoning traces from deepseek-r1, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Synthetic-1: Two million collaboratively generated reasoning traces from deepseek-r1, 2025

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:10.529054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2a1259fe-f11a-455b-9049-eb0266b843d1 · outbound

This paper cites Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation.

Think Only When You Need with Large Hybrid-Reasoning Models Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.270809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3407b5e5-f555-4074-a656-535baa5b0ffc · outbound

This paper cites s1: Simple test-time scaling.

Think Only When You Need with Large Hybrid-Reasoning Models s1: Simple test-time scaling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.396049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db651975-7325-4fee-8d08-61b9c3d2d262 · outbound

This paper cites Openai gpt-4.5 system card.

Think Only When You Need with Large Hybrid-Reasoning Models Openai gpt-4.5 system card

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:10.303703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1f51961e-61a5-416b-8683-f1b618632f5e · outbound

This paper cites Codeforces.

Think Only When You Need with Large Hybrid-Reasoning Models Codeforces

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.669215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7533716-0534-4be9-87c0-ffd0695bd9a7 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Think Only When You Need with Large Hybrid-Reasoning Models Direct preference optimization: Your language model is secretly a reward model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.783845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dd2c238-f4b8-4d16-9d22-c442ad2fd0ec · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:06.927043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8057ca5a-8f4c-4009-af6b-087baae7ef50 · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.046362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b2bf7a-c4d3-46e2-bdcd-e7794f6878d1 · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.201561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25224b00-7549-49f9-be9f-1ee1602fc7f7 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Think Only When You Need with Large Hybrid-Reasoning Models HybridFlow: A Flexible and Efficient RLHF Framework

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.281547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3da7e1f6-03a9-4a55-81b7-6676fba6cf84 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

Think Only When You Need with Large Hybrid-Reasoning Models Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.425645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c651c1ea-e9f7-4746-9a6f-cb553169bdde · outbound

This paper cites Open Thoughts.

Think Only When You Need with Large Hybrid-Reasoning Models Open Thoughts

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.549965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83313ddc-5ae2-49d2-a188-d8f26fdcdd85 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Think Only When You Need with Large Hybrid-Reasoning Models Chain-of-thought prompting elicits reasoning in large language models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.667246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27a3f907-0e81-4c9a-8714-5be174e0e325 · outbound

This paper cites Teaching language models to critique via reinforcement learning.

Think Only When You Need with Large Hybrid-Reasoning Models Teaching language models to critique via reinforcement learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:07.813994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0890e113-2653-46f3-b9ae-affb29002967 · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

Think Only When You Need with Large Hybrid-Reasoning Models Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 46

Resolution: malformed identifier; no resolver link, observed 2026-08-07T15:37:07.954014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b54a3d3-1f3d-41ea-bcd8-e461a2f45e5f · outbound

This paper cites Kodcode: A diverse, challenging, and verifiable synthetic dataset for coding, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Kodcode: A diverse, challenging, and verifiable synthetic dataset for coding, 2025

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.071421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2a5f7e-7a87-416e-935b-345a2b7b87a8 · outbound

This paper cites Limo: Less is more for reasoning, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models Limo: Less is more for reasoning, 2025

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.235606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bae6449-bd68-4026-bb9b-cde7fffb9001 · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.367668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9a1f93-1b18-4fe7-bfe4-4b4cef12a26f · outbound

This paper cites Qwen2.5 Technical Report.

Think Only When You Need with Large Hybrid-Reasoning Models Qwen2.5 Technical Report

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.519460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 717989c8-9e17-404a-86d0-ecbca2861eaa · outbound

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

Think Only When You Need with Large Hybrid-Reasoning Models Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.612688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f4cc201-e3e8-48d5-827f-537c122ee877 · outbound

This paper cites Tenenbaum, and Chuang Gan.

Think Only When You Need with Large Hybrid-Reasoning Models Tenenbaum, and Chuang Gan

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:08.717669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9516010-d52e-479f-b09b-b2df2c742cf0 · outbound

This paper cites Wildchat: 1m chat GPT interaction logs in the wild.

Think Only When You Need with Large Hybrid-Reasoning Models Wildchat: 1m chat GPT interaction logs in the wild

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:10.070000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 046f9701-2421-4d16-8269-2c0146556b93 · outbound

This paper cites 1.4 million open-source distilled reasoning dataset to empower large language model training, 2025.

Think Only When You Need with Large Hybrid-Reasoning Models 1.4 million open-source distilled reasoning dataset to empower large language model training, 2025

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:37:09.810091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ac801e08-10be-4f01-8df2-481f0e76f39a · outbound

This paper cites Language agent tree search unifies reasoning acting and planning in language models, 2024.

Think Only When You Need with Large Hybrid-Reasoning Models Language agent tree search unifies reasoning acting and planning in language models, 2024

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:09.098245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7075ccf1-0a07-480b-8316-aaba5b244fde · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

Think Only When You Need with Large Hybrid-Reasoning Models Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:09.232525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7b95b0bf-bfc5-4c36-a823-b52e471b94d0 · inbound

How Far Are We from Optimal Reasoning Efficiency? cites this paper.

How Far Are We from Optimal Reasoning Efficiency? Think Only When You Need with Large Hybrid-Reasoning Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:49:36.120187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc616748-2b5f-4756-b9d2-4324b1ef92d4 · inbound

Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task cites this paper.

Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task Think Only When You Need with Large Hybrid-Reasoning Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T01:05:26.835657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee207456-fbe3-4f58-ae61-6c7c64b52dd9 · inbound

KAT-V1: Kwai-AutoThink Technical Report cites this paper.

KAT-V1: Kwai-AutoThink Technical Report Think Only When You Need with Large Hybrid-Reasoning Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:29.688777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deeda259-d89e-4528-877a-206597c2a1cf · 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 Think Only When You Need with Large Hybrid-Reasoning Models

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:55.825220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b175c513-4c90-447c-a019-188be8758e66 · inbound

MUR: Momentum Uncertainty guided Reasoning for Large Language Models cites this paper.

MUR: Momentum Uncertainty guided Reasoning for Large Language Models Think Only When You Need with Large Hybrid-Reasoning Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T03:37:01.259623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8fbc63a1-844d-42c5-b21d-2f4f8e4f0de4 · inbound

Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation cites this paper.

Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation Think Only When You Need with Large Hybrid-Reasoning Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T04:17:03.364841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e0714b9d-f4a4-46c2-9aee-ba6de4f8bcca · inbound

Hierarchical Budget Policy Optimization for Adaptive Reasoning cites this paper.

Hierarchical Budget Policy Optimization for Adaptive Reasoning Think Only When You Need with Large Hybrid-Reasoning Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:31:28.102020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e746a584-e3c8-451f-9faa-cd3802a6abca · inbound

Matching Game Preferences Through Dialogical Large Language Models: A Perspective cites this paper.

Matching Game Preferences Through Dialogical Large Language Models: A Perspective Think Only When You Need with Large Hybrid-Reasoning Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T13:54:26.778546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11a487ad-e7a2-4edf-88fa-750f4e1bae50 · inbound

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle cites this paper.

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle Think Only When You Need with Large Hybrid-Reasoning Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T16:07:31.525481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c09e99f-430d-41c8-82e7-a477716cc7bd · inbound

AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification cites this paper.

AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification Think Only When You Need with Large Hybrid-Reasoning Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T13:51:51.270386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba7e694-be8b-4db0-980b-3a00d60f2403 · inbound

TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning cites this paper.

TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning Think Only When You Need with Large Hybrid-Reasoning Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T15:51:05.439841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e0925b38-4263-4386-893c-7b67fdfbc585 · inbound

ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure cites this paper.

ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure Think Only When You Need with Large Hybrid-Reasoning Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T05:43:53.786778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f7b5512-257c-4ef5-bd9d-7048e409a4fc · inbound

Efficient Reasoning on the Edge cites this paper.

Efficient Reasoning on the Edge Think Only When You Need with Large Hybrid-Reasoning Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00073c2d-6880-4c3e-b99d-7a8d455b29fd · inbound

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation cites this paper.

HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation Think Only When You Need with Large Hybrid-Reasoning Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T07:41:01.533819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d759670c-2a0f-4c74-8a18-ff337e9b1510 · inbound

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning cites this paper.

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning Think Only When You Need with Large Hybrid-Reasoning Models

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T23:15:48.850663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0fefb37d-7c46-4e3b-90ba-e917fb90336a · inbound

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning cites this paper.

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning Think Only When You Need with Large Hybrid-Reasoning Models

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:34:41.000756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4dc2f30-c3a2-43f4-9a57-c6458cde1fa5 · inbound

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions cites this paper.

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions Think Only When You Need with Large Hybrid-Reasoning Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:15:23.473176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.