Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions | Paper Citation Record

Observation 0891c03e-988f-42cd-a3ac-fd3906027c5c · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.381687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c36e2aa2-dddd-4b9f-8ad9-d3efbd6dba4a · outbound

This paper cites Premise Order Matters in Reasoning with Large Language Models.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Premise Order Matters in Reasoning with Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.393854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83981d8-74c8-47f8-a28f-2c9ac2de0c19 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.558711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fe0929f2-58b3-4975-ad88-f4d9660e598b · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.405041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e1e360-8a89-4ce2-8d9d-af3e6c2c3996 · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.411594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c57a66f6-4f08-4414-8a31-2b777c9bb3e9 · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.418167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e7f929-a5dc-4b72-8170-ebab30d6c697 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.424280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e47091e-8d91-4802-81ab-6b8ddc677b58 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.430149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6d51948-8216-4452-8b06-68d01df07c02 · outbound

This paper cites Kellerer, U.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Kellerer, U

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.532325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3c6dd6a1-36d0-49b6-8aeb-ab5015f5a77e · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.516312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1e79231b-cca8-42a1-9d4b-4dee816e09aa · outbound

This paper cites Steering LLM Thinking with Budget Guidance.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Steering LLM Thinking with Budget Guidance

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.462106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e57ea4b-313a-4452-a4e9-161eb44a12a2 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.498825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f008bbcc-ddb5-42f5-b4c6-d5d72b81d7c3 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.486912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ece181-3732-4ea9-8ecb-a90cab3e0bf5 · outbound

This paper cites Reasoning Models Can Be Effective Without Thinking.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Reasoning Models Can Be Effective Without Thinking

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.491586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc92b89-b4be-47bb-a969-985b81d8c48f · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.496684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4097c561-8b8b-4b14-9927-e606ce78acc5 · outbound

This paper cites TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.501928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2a0aaa-5ab1-41a0-bff7-27a6ecf49724 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.471240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c6db5c40-fc03-4847-ac89-107798b2046b · outbound

This paper cites REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.511851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beebbebd-9086-4016-8b42-1306fe843472 · outbound

This paper cites Rational Metareasoning for Large Language Models.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Rational Metareasoning for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.521998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc18ca5-f88c-4971-a7ee-36d18c3ec20e · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.543400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd844c39-f763-4009-9e15-a3f753baf526 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.453760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d4ad9fbb-b4c6-49de-964f-7a84176a9530 · outbound

This paper cites Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.568541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcb8b2a7-93ca-4f65-a19e-8fd4e12ef664 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.578422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b39a9677-0307-4ab6-a7ff-8cf411dd56b2 · outbound

This paper cites MathArena: Evaluating LLMs on Uncontaminated Math Competitions.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions MathArena: Evaluating LLMs on Uncontaminated Math Competitions

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.583289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45f94fae-51f0-4902-bd1c-e8990381356b · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.589452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e114142-68e6-4629-954e-0dcb0aead0b3 · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.594821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c015ef6-7e48-4ac5-95ca-90e522f7331f · outbound

This paper cites The Effect of Question Order on Evaluations of Test Performance: Can the Bias Dissolve? , volume =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions The Effect of Question Order on Evaluations of Test Performance: Can the Bias Dissolve? , volume =

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.414589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ba45cc57-223f-44cf-86dc-15abd0162483 · outbound

This paper cites Understanding performance in test taking: The role of question difficulty order , journal =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Understanding performance in test taking: The role of question difficulty order , journal =

Reference 43

Resolution: metadata mismatch; raw_fallback, observed 2026-08-12T00:41:02.241180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e8c72946-d379-430f-9aeb-89e3e3c4af94 · outbound

This paper cites OpenAI o1 System Card.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions OpenAI o1 System Card

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.609543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55998d3f-17e5-4bfd-8587-90bded5b3992 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.614586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f470ac4-f768-4691-802c-89033cc50e1a · outbound

This paper cites 2021 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2021 , eprint=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.619578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795537d0-59c4-476c-86c5-e73905d11ff1 · outbound

This paper cites Measuring Ability, Speed, or Both?.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Measuring Ability, Speed, or Both?

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.388812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 350b0fbc-d7b7-4807-b199-e8926f936f96 · outbound

This paper cites Psychometrika , volume =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Psychometrika , volume =

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.372489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 001aa04a-5ac8-48ec-a9a2-68fc9acfb8e3 · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.356293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e1bdc7b8-79cf-400b-9de3-b99a641633e8 · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.640765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bcb5397-d6e6-4001-9c58-d7b5bd071713 · outbound

This paper cites 2020 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2020 , eprint=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.645577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e70bca9-47d7-4deb-bc36-406e3eae3244 · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.650361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f1daf1-95da-463a-b1f1-7908065d13f1 · outbound

This paper cites Evolving Deeper LLM Thinking.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Evolving Deeper LLM Thinking

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.656428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ceba4bb-969b-478e-bb53-43a61de675a4 · outbound

This paper cites 2024 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , eprint=

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.319334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0afa5ae3-5579-49a0-8878-ddaf68aca01d · outbound

This paper cites 2023 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2023 , eprint=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.667203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62adc81c-13e1-4cd9-8521-c94532b63b15 · outbound

This paper cites Proceedings of the 36th International Conference on Neural Information Processing Systems , articleno =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Proceedings of the 36th International Conference on Neural Information Processing Systems , articleno =

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.672029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bccdd1a9-195e-490f-9d73-b5533fa81f27 · outbound

This paper cites Schoenfeld ' s Anatomy of Mathematical Reasoning by Language Models.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Schoenfeld ' s Anatomy of Mathematical Reasoning by Language Models

Reference 57

Resolution: verified exact; doi, observed 2026-08-12T00:41:01.967492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87c1fbc0-91a5-47d6-bc82-08e7a14ae4aa · outbound

This paper cites Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld ' s Episode Theory.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld ' s Episode Theory

Reference 58

Resolution: verified exact; doi, observed 2026-08-12T00:41:01.951197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c2f0bd4d-10fd-4f94-86c0-51eee048dfce · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.280796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c9b354db-faa9-44bf-bb77-5634779ce537 · outbound

This paper cites What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding

Reference 60

Resolution: metadata mismatch; local_arxiv, observed 2026-08-12T00:41:02.735307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f66e0b5-2fe1-4d42-9543-1d71769311f5 · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.695485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3455fa06-2855-4bda-862e-b851fa9c29ce · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.264513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5b9e465d-b957-4c2a-b2aa-2170b8c8427a · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.705148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44707f9-d51e-4c70-a5b6-d4256a2d8496 · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.238318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 98d29c6a-0a6b-4fc7-8ce3-8d88fe6a8eb8 · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.714733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322d5b22-2436-4e40-a8e9-16bbc7dbf61a · outbound

This paper cites 2024 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , eprint=

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.221633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4b6aa461-d16e-4b0f-b6e5-8317963f8672 · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.204686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c748bad4-2fa2-4962-90c6-48c9fb9b5267 · outbound

This paper cites 2505.20258 , archivePrefix=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2505.20258 , archivePrefix=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.729410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e949ab87-ba76-4f22-aed5-5cbfbe4e212a · outbound

This paper cites 2024 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , eprint=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.734397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbd94739-535e-4012-9b3a-ffe34c4b2c87 · outbound

This paper cites Steering.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Steering

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.177594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 23abf3c3-4f00-4931-a3ac-1772b18e96d5 · outbound

This paper cites BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.746514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffd88c9-8457-48b3-bd33-cca9bd3daf2b · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Token-Budget-Aware LLM Reasoning

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.751553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 959fcbcb-80ee-404e-87c5-b834383b7dea · outbound

This paper cites The Llama 3 Herd of Models.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions The Llama 3 Herd of Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.756037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b883ea27-5b70-493d-8bfa-8f0366f8e815 · outbound

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

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.760731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ba01e8-73bc-4b8e-af1c-bded7e17838e · outbound

This paper cites Qwen3 Technical Report.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Qwen3 Technical Report

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.765737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cadad6-4259-4a96-8b7f-7b2136aa0340 · outbound

This paper cites 2025 , school=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , school=

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.161418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation de346e61-1bbc-4026-bc20-66a0efc73ead · outbound

This paper cites 2024 , editor =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , editor =

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.775466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59c9d35d-7aa3-4063-a868-836b6b2e5c2d · outbound

This paper cites Vicky and He, Conghui and Wu, Lijun , journal=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Vicky and He, Conghui and Wu, Lijun , journal=

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.135049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 83b520ca-ec2e-4e2b-bd0b-f03bfd6dd464 · outbound

This paper cites an unresolved cited work.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-12T00:41:03.119699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c2ab9dbb-bc4a-46fe-9148-3d0a003d66ef · outbound

This paper cites Triage: Evaluating Prospective Metacognitive Control in.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Triage: Evaluating Prospective Metacognitive Control in

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.103967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e15344c-3520-43e3-857e-eb72744a3d88 · outbound

This paper cites 2026 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2026 , eprint=

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.796046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28dbad17-7757-4a1c-996e-a8c882072226 · outbound

This paper cites 2004 , publisher=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2004 , publisher=

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.076743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2fd2b7ff-db75-487d-82ef-ab8932557dc4 · outbound

This paper cites Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track , pages=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track , pages=

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.059676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation df540463-70bf-485e-8bca-aecadff2c02c · outbound

This paper cites Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM ^2 ) , pages=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM ^2 ) , pages=

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.042496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c10b7745-4918-4cb8-913b-893c5a6ce7b6 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Findings of the Association for Computational Linguistics: ACL 2025 , pages=

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.024975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3d865c5b-efd8-4067-a03e-8049daa54a6e · outbound

This paper cites 2024 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , eprint=

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:03.007398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 35c98bfe-2135-41a1-aa2e-6458714b4200 · outbound

This paper cites Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.826544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf4188b-1747-4ee4-addf-dbe0e0d42191 · outbound

This paper cites and Ballesteros, Miguel and Chilton, Lydia and Yu, Zhou and Roth, Dan.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions and Ballesteros, Miguel and Chilton, Lydia and Yu, Zhou and Roth, Dan

Reference 88

Resolution: verified exact; doi, observed 2026-08-12T00:41:01.900187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c7787c17-3336-4180-b41d-0e10a91e2453 · outbound

This paper cites 2026 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2026 , eprint=

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:02.991643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87c1132b-c7f8-47db-b4c4-8d86ccce8c87 · outbound

This paper cites 2024 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2024 , eprint=

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:02.974821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 299e3819-bc02-4c5a-9cce-e15092b510e0 · outbound

This paper cites Characterizing Positional Bias in Large Language Models: A Multi-Model Evaluation of Prompt Order Effects.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Characterizing Positional Bias in Large Language Models: A Multi-Model Evaluation of Prompt Order Effects

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.845697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aba4f11-beef-4dbe-bc1e-3d42135e1f73 · outbound

This paper cites Principles of metareasoning , journal =.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions Principles of metareasoning , journal =

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:01.850325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2920928-d2d5-4446-b23c-6b23f33e40ec · outbound

This paper cites 2025 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2025 , eprint=

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:02.958973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f97fd9d8-20b2-43b8-a8ba-735b0db5ee21 · outbound

This paper cites 2026 , eprint=.

Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions 2026 , eprint=

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:41:02.942367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers