Paper Citation Record · LEDGER

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

As of 15 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 5 inbound Pith citation observations for arXiv:2506.18237.

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

pith.paper-citation-record.v1
2506.18237 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:28:41.497380Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T08:09:52.972532Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T22:25:39.517114Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy4
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f17b4c46-bbd7-4971-a1c7-f5b5585aad04 · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:36.724742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37d72e08-9e21-471a-b5d0-857ff25dcf3b · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:36.788614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c5096e-6144-4ae9-be1b-08cab1655567 · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:36.942227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c7f70ea-0ad3-403a-a856-46924bee4374 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Token-Budget-Aware LLM Reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.065480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f84dbad1-3d81-40f6-ba45-483941eaa666 · outbound

This paper cites The impact of reasoning step length on large language models.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model The impact of reasoning step length on large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:28:43.105111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 30db8791-896d-425b-9c11-d5497c67957a · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model C3ot: Generating shorter chain-of- thought without compromising effectiveness

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.304745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7659bb44-44de-4f05-b2e4-a30d560d3f6d · outbound

This paper cites VinePPO: Refining Credit Assignment in RL Training of LLMs.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model VinePPO: Refining Credit Assignment in RL Training of LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.524741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a7aabb6-5f76-46eb-9799-f7c11e1203a4 · outbound

This paper cites LLM Post-Training: A Deep Dive into Reasoning Large Language Models.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model LLM Post-Training: A Deep Dive into Reasoning Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.684822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a453f98f-0bc6-4b5c-b537-0675678ee81e · outbound

This paper cites AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.815034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8df86ba-8f02-41cb-afa5-534b6ed37449 · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:37.939029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3751446f-e19e-4344-aded-4380b4983e01 · outbound

This paper cites Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:38.124748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edab26c8-8e1a-4930-ad96-a80a54a2a313 · outbound

This paper cites Peft: State-of-the-art parameter-efficient fine-tuning methods.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Peft: State-of-the-art parameter-efficient fine-tuning methods

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:38.341898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d0f8f9-75ae-4667-bab6-dc0ebb366f70 · outbound

This paper cites SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:38.512970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d105e50-c585-4d6b-b683-df77404e5c33 · outbound

This paper cites s1: Simple test-time scaling.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model s1: Simple test-time scaling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:38.697944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5621987e-1cbb-4c3b-abc2-49183719e93e · outbound

This paper cites Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:38.873840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0eb64d0-8518-4b30-bd0a-13a64513ced2 · outbound

This paper cites Learning to reason with LLMs.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Learning to reason with LLMs

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:28:42.894007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 66eae5e8-f01a-4bf3-bffd-b34e62915fab · outbound

This paper cites The benefits of a concise chain of thought on problem- solving in large language models.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model The benefits of a concise chain of thought on problem- solving in large language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:28:42.608172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 36ab0612-a4a0-4de0-ab01-62e0d8d342b1 · outbound

This paper cites Self-Reflection in LLM Agents: Effects on Problem-Solving Performance.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:39.415341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c2c593-603d-45e2-82f6-8e6c659c86d0 · outbound

This paper cites Self-critiquing models for assisting human evaluators.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Self-critiquing models for assisting human evaluators

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:39.540270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f604a5e2-42d6-4142-893b-39539c96e298 · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:39.674751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57ebf6f-ff97-4d80-9185-64b7f3245ed0 · outbound

This paper cites Dast: Difficulty-adaptive slow-thinking for large reasoning models.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Dast: Difficulty-adaptive slow-thinking for large reasoning models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:39.864875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7497aae9-88a9-4476-810e-5e67929474ad · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:39.995135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c448b801-d684-4c19-b4ec-2641f31f6878 · outbound

This paper cites Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:40.224745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a2fb81-3969-4bd0-a297-8648cc60aba8 · outbound

This paper cites Large language models are better reasoners with self-verification.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Large language models are better reasoners with self-verification

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:40.338404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f551bb4-1332-4a89-bec4-7bfc7e896921 · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:40.484741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe89364-6f1e-4824-b5d1-26b29b027228 · outbound

This paper cites A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:40.648243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb6d995-c077-4221-8c79-9337840dddaf · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Chain of Draft: Thinking Faster by Writing Less

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:40.811546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e46c1f1-8574-4a23-b441-1c038261c194 · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:41.000596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52be73b3-2e0c-44c3-a792-35d4179d01d4 · outbound

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:41.164788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef670f0a-6fbe-4d06-9322-eeac51fcc7e5 · outbound

This paper cites SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:28:41.334745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c957f00-aa99-46a7-ac0a-dd943db413ce · outbound

This paper cites Branch-Extension.

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model Branch-Extension

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:28:42.388457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation 5cf323ed-ea45-4fa9-a29d-36bcd973a7c4 · inbound

Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking cites this paper.

Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T08:09:52.972532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd2a054-c218-41d7-a08c-4b1421badcb5 · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:51:30.150918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f7cfc255-5ae2-4bea-9a99-5e86b91588df · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:15:03.277972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 24ad31e4-282f-4449-9193-27b8ccbde130 · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 119

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:55.833122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3131f75a-e836-4b65-9e7d-5f7bd9109e76 · inbound

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization cites this paper.

Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization AdapThink: Adaptive Thinking Preferences for Reasoning Language Model

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:25:39.518829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.