What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding | Paper Citation Record

Observation a55a1a08-e18a-4b24-9247-cb13c684c169 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding L1: Controlling how long a reasoning model thinks with reinforcement learning, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.081109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c7a231-05a7-4f43-bf71-43e249e2802a · outbound

This paper cites Large language models for mathematical reasoning: Progresses and challenges.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Large language models for mathematical reasoning: Progresses and challenges

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:21.016890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e337d52b-edce-41c4-81dd-4fab18c56fb6 · outbound

This paper cites AIME 2022–2024 Validation Set, 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding AIME 2022–2024 Validation Set, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.993151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fed927cd-a079-4401-8e35-028ca8c2a49c · outbound

This paper cites AMC 12 2023 Integer-Answer Validation Set, 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding AMC 12 2023 Integer-Answer Validation Set, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.976092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c956cfc0-c7d9-4d08-83b8-56b76314b2a1 · outbound

This paper cites Reasoning language models: A blueprint, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reasoning language models: A blueprint, 2025

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.957371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c1ec5b4c-28e5-41e7-9af5-c6fe5047ed0f · outbound

This paper cites Data diversity matters for robust instruction tuning, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Data diversity matters for robust instruction tuning, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.939047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c32e16d2-6937-460e-8007-4548de2a0152 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.146136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bdda8d5-fc92-4ad0-af8e-34b07140ee82 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.155739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3812779-49a9-4b22-8de3-a20b8b04dd0c · outbound

This paper cites Alpagasus: Training a better alpaca with fewer data, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Alpagasus: Training a better alpaca with fewer data, 2023

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.922158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae07a26e-c572-4912-98a7-60a14423c346 · outbound

This paper cites Towards reasoning era: A survey of long chain-of-thought for reasoning large language models, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Towards reasoning era: A survey of long chain-of-thought for reasoning large language models, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.172782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6165a161-d4dd-4bd9-8a99-aead95d924fd · outbound

This paper cites Extracting and Understanding the Superficial Knowledge in Alignment.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Extracting and Understanding the Superficial Knowledge in Alignment

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:52:20.121950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 46932ad1-71a6-478d-86f2-ddf90e4a96a4 · outbound

This paper cites Do not think that much for 2+3=? on the overthinking of o1-like llms, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Do not think that much for 2+3=? on the overthinking of o1-like llms, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.892877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f9c5f84e-cabe-41d9-b203-f4d46e5b9038 · outbound

This paper cites Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.205625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c1f8511-47dd-497f-a5e6-c03a0e799d3c · outbound

This paper cites Gonzalez.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Gonzalez

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.874276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 01ff8063-1311-4c39-984e-9f6bb25d505e · outbound

This paper cites Process reinforcement through implicit rewards, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Process reinforcement through implicit rewards, 2025

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.858576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 57da4753-147b-4ee5-8eaf-741ec4d11cbd · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.842891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 124088ec-e383-4823-b8bb-047437c96ba0 · outbound

This paper cites Mods: Model-oriented data selection for instruction tuning, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Mods: Model-oriented data selection for instruction tuning, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.824884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7491c215-0c03-4e79-aecf-657cae47dd5f · outbound

This paper cites Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.240527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89af4f56-187f-42a1-bd16-61758b633dd9 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Token-Budget-Aware LLM Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.246347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9301f3c-e331-433b-a8ec-c071bb31695d · outbound

This paper cites Reproduce the inference-time scaling experiment, 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reproduce the inference-time scaling experiment, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.809286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 91cc1aa1-61a6-4203-91d2-186e0962c3e0 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Training Large Language Models to Reason in a Continuous Latent Space

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.262129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d407c180-26bf-4782-8967-4a133b8645cc · outbound

This paper cites Towards reasoning in large language models: A survey, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Towards reasoning in large language models: A survey, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.272762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9354e951-1a5e-4436-bfe2-692c3e599e82 · outbound

This paper cites Collaborative decoding of critical tokens for boosting factuality of large language models.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Collaborative decoding of critical tokens for boosting factuality of large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.278157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e42f6d95-473a-4bf2-9b43-c94e3a218019 · outbound

This paper cites macmillan, 2011.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding macmillan, 2011

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.286432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81459243-8805-41a0-9c20-6e9c9da20edc · outbound

This paper cites Overthink: Slowdown attacks on reasoning llms, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Overthink: Slowdown attacks on reasoning llms, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.766821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 710462df-e4d4-40bc-ba93-d7b1f6a7556c · outbound

This paper cites Fast inference from transformers via speculative decoding.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Fast inference from transformers via speculative decoding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.308495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9d1807a-335f-4c64-b3c6-89c2ed254872 · outbound

This paper cites Superficial safety alignment hypothesis.arXiv preprint arXiv:2410.10862, 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Superficial safety alignment hypothesis.arXiv preprint arXiv:2410.10862, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.316709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e35b196-19af-4cd3-b874-31c6dd410f49 · outbound

This paper cites RuleR: Improving LLM Controllability by Rule-based Data Recycling.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding RuleR: Improving LLM Controllability by Rule-based Data Recycling

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:52:19.832605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c90ef284-1f4c-4187-915c-c5911981ca86 · outbound

This paper cites Selective reflection-tuning: Student-selected data recycling for LLM instruction-tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Selective reflection-tuning: Student-selected data recycling for LLM instruction-tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.732249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14858250-3ddc-419b-9d6c-04c16573b6ac · outbound

This paper cites Reflection-tuning: Recycling data for better instruction-tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reflection-tuning: Recycling data for better instruction-tuning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.699661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6af645dc-ff40-49b0-a71a-43f22fe11a03 · outbound

This paper cites Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.377193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850ffb49-167d-49ec-a6ea-77e74aabfc8b · outbound

This paper cites How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.384607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b26c2b7-7cf4-4c1d-9933-cff2d5aae3f3 · outbound

This paper cites What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.391931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26e46771-ee38-46e1-ac83-4bc233e5432e · outbound

This paper cites Superfiltering: Weak-to-strong data filtering for fast instruction-tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Superfiltering: Weak-to-strong data filtering for fast instruction-tuning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.674612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a62af263-e29c-48b6-8e69-ef6bef0b3c06 · outbound

This paper cites From quantity to quality: Boosting LLM performance with self- guided data selection for instruction tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding From quantity to quality: Boosting LLM performance with self- guided data selection for instruction tuning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.640628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85195145-3a7b-4202-bf09-84b3adef7e64 · outbound

This paper cites Contrastive Decoding: Open-ended Text Generation as Optimization.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.421751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2319720-7c1e-4432-b8a5-215e6a41aac0 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding From system 1 to system 2: A survey of reasoning large language models, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.434399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ce5cfc-5745-4f52-bb92-fee9490dc8af · outbound

This paper cites Reward-Guided Speculative Decoding for Efficient LLM Reasoning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.444052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e2e17e9-d2b9-4806-b559-7c3a1c1a7414 · outbound

This paper cites Let's Verify Step by Step.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Let's Verify Step by Step

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.458905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d13333a-89f9-4752-a905-4f0fee3be0f9 · outbound

This paper cites The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.466703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7539f4f-0abe-4227-a320-cfa788dad150 · outbound

This paper cites Code- mind: A framework to challenge large language models for code reasoning, 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Code- mind: A framework to challenge large language models for code reasoning, 2024

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.589018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb34d5ef-469a-4247-82e9-09d0c5df819d · outbound

This paper cites What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.489295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f57cc8-7f29-46c4-8c5f-bbf5790be1e1 · outbound

This paper cites TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.498481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 062f1f51-9ce9-428e-ad44-bd6a9808cc34 · outbound

This paper cites Efficient inference for large reasoning models: A survey, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Efficient inference for large reasoning models: A survey, 2025

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.553672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89abee34-17a8-4734-b669-a33f132e4dc2 · outbound

This paper cites O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning, 2025

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.513815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d70d71ce-c721-4a2b-98ec-34d1bdb20518 · outbound

This paper cites s1: Simple test-time scaling, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding s1: Simple test-time scaling, 2025

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.522951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4612888-e565-4e51-9945-dc896d1b4fd1 · outbound

This paper cites OpenAI o1 System Card, December 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding OpenAI o1 System Card, December 2024

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.533667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21a4e952-2129-4d87-8e9c-18d55b1acaa5 · outbound

This paper cites A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond, 2025

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.544037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5136668f-fe2a-4634-ad02-69ff93888179 · outbound

This paper cites Revisiting the Superficial Alignment Hypothesis.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Revisiting the Superficial Alignment Hypothesis

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.555302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcd97adf-d770-42b7-85ad-c35500eb67c0 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Gpqa: A graduate-level google-proof q&a benchmark

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.562339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bad6c74-8c84-4b61-87f0-c75c4632ddf9 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding The benefits of a concise chain of thought on problem- solving in large language models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.569488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d5e9bf-dc59-4ffd-b536-f30c1d2c52ee · outbound

This paper cites an unresolved cited work.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.582565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92e8a7bb-c1f2-4b85-977f-36d960b88dfc · outbound

This paper cites Learning to Decode Collaboratively with Multiple Language Models.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Learning to Decode Collaboratively with Multiple Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.590507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44fa246-e8e8-41cc-9e6f-3515bba747be · outbound

This paper cites Efficient Reasoning with Hidden Thinking.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Efficient Reasoning with Hidden Thinking

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.599257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fcce375-b43e-4b37-8c90-f8ab639f9b45 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.606294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e64643e9-308e-44e5-84dd-f1302b09ac92 · outbound

This paper cites Fast Best-of-N Decoding via Speculative Rejection.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Fast Best-of-N Decoding via Speculative Rejection

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.612719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 319c74bc-a4fe-48bc-b193-e4de6ee4598d · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.619379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72d49ec-9c03-4415-a114-ca6870f90b57 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Qwen2.5: A party of foundation models, September 2024

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.628264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fed01112-6437-48f5-9824-68420ad2ab69 · outbound

This paper cites Qwen3, April 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Qwen3, April 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.634818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e304cca-d0db-4a49-b061-66cbeff00e22 · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Llama 2: Open foundation and fine-tuned chat models, 2023

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.408309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4019b593-75cf-47c0-9581-9e6f7f67f444 · outbound

This paper cites Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.648073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73127110-abe6-4cc4-9e98-5bb17a5fec37 · outbound

This paper cites SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.654116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b54b5691-eafa-49dc-87b5-550f54f6c437 · outbound

This paper cites Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.661384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0798781e-ecbc-47a2-85d0-3f8cf615c646 · outbound

This paper cites Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.668518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42350a00-1c17-4e42-ae75-b6d9230afdad · outbound

This paper cites Multimodal chain-of-thought reasoning: A comprehensive survey, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Multimodal chain-of-thought reasoning: A comprehensive survey, 2025

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.388342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2d1f5401-e14c-4f07-a736-55580940e561 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models, 2023.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Chain-of-thought prompting elicits reasoning in large language models, 2023

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.682613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eebc5919-4411-4ec2-891c-a5f90ceaf5b5 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding When More is Less: Understanding Chain-of-Thought Length in LLMs

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.687764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef8202b-3ab2-47c0-a35c-37103c156ebb · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067, 2025

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.694097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca804117-5b32-4cce-8081-768476b9c7d8 · outbound

This paper cites Evaluating mathematical reasoning beyond accuracy, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Evaluating mathematical reasoning beyond accuracy, 2025

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.355286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 808d93ca-bfa5-4bb6-ab6e-b4f49334e010 · outbound

This paper cites Self- rewarding correction for mathematical reasoning, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Self- rewarding correction for mathematical reasoning, 2025

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.332254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0975db52-ade9-4c12-9478-9b67ba297715 · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Chain of Draft: Thinking Faster by Writing Less

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.709683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 921387af-cf4c-49ca-aa3b-d654b9bccbc5 · outbound

This paper cites A Survey on Knowledge Distillation of Large Language Models.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding A Survey on Knowledge Distillation of Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.716069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc87fb3-dd29-43fd-a776-8a0a96d30319 · outbound

This paper cites Speculative thinking: Enhancing small-model reasoning with large model guidance at inference time, 2025.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Speculative thinking: Enhancing small-model reasoning with large model guidance at inference time, 2025

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.302726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f64cde8d-47ba-4670-8bfb-fddf3e899c7d · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Limo: Less is more for reasoning, 2025

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.729575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd60d37c-3213-4e06-b499-7b1b6659cc6e · outbound

This paper cites Distilling System 2 into System 1.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Distilling System 2 into System 1

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.741862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2949428b-8459-4018-aba0-892a7f70b29b · outbound

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

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Lightthinker: Thinking step-by-step compression.arXiv preprint arXiv:2502.15589, 2025

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.747356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fc39cd8-7b90-4396-ba62-d5c6921bb653 · outbound

This paper cites overthinking.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding overthinking

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.250168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6f862345-c001-49c0-80e1-01e3dfb86e8b · outbound

This paper cites superficial.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding superficial

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:52:20.216457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bbb2b939-ec51-431d-a773-8587325672fe · outbound

This paper cites amateur” model alongside a strong “expert.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding amateur” model alongside a strong “expert

Reference 80

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T05:52:18.959209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ebc7f781-c373-4d5c-aa1f-477da3b00fa9 · outbound

This paper cites an unresolved cited work.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.357209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers