Pith. sign in

Paper Citation Record · LEDGER

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 55 inbound Pith citation observations for arXiv:2501.18585.

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

pith.paper-citation-record.v1
2501.18585 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T22:58:24.015239Z

measured 86 of 86 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 55 of 55 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T06:04:14.514628Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

31 of 31 outbound references displayed

  • verified exact1
  • verified fuzzy8
  • unresolved22
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation df689823-d146-4f7f-aa9e-9af02e2ab968 · outbound

This paper cites write newline.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.462247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.462247Z digest=sha256:3e6f157bc03513a8fbb8cafef7ef76ffe3eae5f2b275afde47e6c7572f2b55fb

Observation 0cee5ad9-f3b9-4a76-bc3c-f1e0e28a6b64 · outbound

This paper cites Phd knowledge not required: A reasoning challenge for large language models.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Phd knowledge not required: A reasoning challenge for large language models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.468103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.468103Z digest=sha256:366c3b40df76c0b039f3fabc701171bf1e5107753ed11b67675e1659ef8351a0

Observation e98627ac-f0b4-460f-95e1-83603904f22c · outbound

This paper cites Training language models to reason efficiently.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Training language models to reason efficiently

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.473526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.473526Z digest=sha256:20f4c1133ca8a80a4528870bbec6ac67bb55d92dfc2be3760c0b97c5394175b5

Observation 346ac0a0-afd6-411c-9273-ced0e523b7f8 · outbound

This paper cites Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-08-09T22:58:24.257713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.480178Z digest=sha256:f231cd492ad5ceb8509637ac3ff3cf54f8682d3e080989acbc6b2c862a69928b

Observation dc33ae71-48be-47de-9265-900cd5e0c2c8 · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.532883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.532883Z digest=sha256:2294c31ab7c4f12b796567e081bbe1f4bef7d33d5a86805ef4dd01503afeee12

Observation 0ae46ce3-88b1-48dd-8f7b-5f7fb626dbef · outbound

This paper cites Improving minimum bayes risk decoding with multi-prompt.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Improving minimum bayes risk decoding with multi-prompt

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.640069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.640069Z digest=sha256:d55318f74b93ebe13792ea1fcb15286bbffeb447e0fd262ebaa04e6726b66207

Observation 2e464694-c2d9-4d50-89d9-f30e44906c8c · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Measuring mathematical problem solving with the MATH dataset

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.742812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.742812Z digest=sha256:bdadc1a7d177b273ba32a9e431ece78e6adef74c07af4b2e92e78c9cdf2f1994

Observation f687658b-4783-47a3-a00e-af796f6ce0d6 · outbound

This paper cites Montreal neural machine translation systems for wmt’15.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Montreal neural machine translation systems for wmt’15

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.999876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.802296Z digest=sha256:05bd8543603c452f116d140df6b75fddd0328d26d17d724e8ee5ed229b21d101

Observation 155d06ff-2cdb-4c2a-a66d-468b4cff7b26 · outbound

This paper cites Args: Alignment as reward-guided search.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Args: Alignment as reward-guided search

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.846104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.846104Z digest=sha256:de40a54624f1fc9dd52f11a2fd9a59530f415de63c0db4cc26557dd2cdb5a6e9

Observation 60e85036-c421-4451-ab38-4a408a371d7b · outbound

This paper cites Kimi k1.5: Scaling reinforcement learning with llms.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Kimi k1.5: Scaling reinforcement learning with llms

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.944189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.869537Z digest=sha256:cb06c4ff66030649e6d3c43236b4c727c0e6eb216cf237a242fd3ab586599c30

Observation 1e63eeca-dc4b-47dd-b448-46a5c25cc402 · outbound

This paper cites Six challenges for neural machine translation.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Six challenges for neural machine translation

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.928610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.910246Z digest=sha256:7c5698df73a97c82965a0dacc07029e4949395a5002522bcf95da514eae05942

Observation baeb21ea-32d5-4a19-987b-6dd7f0c1a953 · outbound

This paper cites Making language models better reasoners with step-aware verifier.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Making language models better reasoners with step-aware verifier

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.914931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.914931Z digest=sha256:3ed5a29d49e79c9160fe6a82509935b47c52399bdea32d1f1129bef6fac9f7be

Observation fe85b898-8949-4e7a-aa54-114bbdec07eb · outbound

This paper cites Let's verify step by step.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Let's verify step by step

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.920087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.920087Z digest=sha256:345ae57af4466b274fdf3f76b56d60b95acf7ad66d504b0998b3273153c8bf0d

Observation e6db5c5f-55f7-43a4-af06-fde053e68fe0 · outbound

This paper cites Aime problems and solutions.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Aime problems and solutions

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.895994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.924769Z digest=sha256:eb4f89af8fdd85c26a2e481385d232672e84bef897dc64abf827d62e8eafc73d

Observation 3fcd58a3-3021-4ec5-9d6e-baf8cf7ffc4a · outbound

This paper cites s1: Simple test-time scaling.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs s1: Simple test-time scaling

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.930507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.930507Z digest=sha256:cee11193b31b76e008f6d2fe56ff9c787c714b759248476ebe13d753c73f96ee

Observation c7bf795f-c475-4691-8ab5-a825ec414487 · outbound

This paper cites Correcting length bias in neural machine translation.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Correcting length bias in neural machine translation

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.877979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.936201Z digest=sha256:dedfd7d0e219008a82ab93c6178c752554f04ca07d8970867f8fe7d52b5309be

Observation 8c96f7f2-aa41-4a0f-afc5-bb60c01e5a1e · outbound

This paper cites Learning to reason with llms.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Learning to reason with llms

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.941336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.941336Z digest=sha256:398bf0f36a18a015ef8b835eba8951ccd4cb59a6eff20365ba1a1705c7de6390

Observation f46f76ef-39c5-4fdc-9ecc-dba856ec9c3c · outbound

This paper cites Let's Think Dot by Dot: Hidden Computation in Transformer Language Models.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Let's Think Dot by Dot: Hidden Computation in Transformer Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.946035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.946035Z digest=sha256:e348ce5a17f3adb03f18e22b3a67c7ba6094231a02fa992300a6e40f68b4f71f

Observation 1a242757-ac17-4135-b8e5-6ac21a8bc663 · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.951230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.951230Z digest=sha256:9375b2899f327dc5fc2f7342319183ecef08f3c3d02f03a76cbe9446ca054ef4

Observation 0cfdc508-8c5e-48ac-af35-51c2196aa46a · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.956484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.956484Z digest=sha256:80c6d5a507136905d0c10af3e2eb5d0910a151b628241d74780ce9717246afe7

Observation 5a099010-2220-4fb8-bc14-ee2df7da7abd · outbound

This paper cites Get to the point: Summarization with pointer-generator networks.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Get to the point: Summarization with pointer-generator networks

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.837957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.961291Z digest=sha256:840f67e4c7ed60a431dc410abdc9743ddedfcb089edeb046938e78b8f87a6045

Observation 91eefb13-b026-4e67-bb60-b97a4dd92555 · outbound

This paper cites Modeling coverage for neural machine translation.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Modeling coverage for neural machine translation

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.820289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.965738Z digest=sha256:a7f51f2c1fd93813ab26c0fb7382d0fb1365cb2781a2ae2835c34e71bb281e6b

Observation 8d08066f-8c32-4175-aadb-227234a4a1e8 · outbound

This paper cites Neural machine translation with reconstruction.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Neural machine translation with reconstruction

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T22:58:24.805199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.970214Z digest=sha256:972ba113dd414c21b1ccf2d0acf869d2afb3b0f5b0aadc89a2f65e4df12d20f9

Observation 4a8e7728-2c68-42b0-883a-f5392df94db4 · outbound

This paper cites Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.975163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.975163Z digest=sha256:70e532729348b9bc52cd81abb9ab11f9e1034247a1f973dda48e95b6cd2e0942

Observation dac93af1-5337-4604-8517-8a74ae8c02bb · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Chain-of-thought prompting elicits reasoning in large language models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.984063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.984063Z digest=sha256:565a96d344c89b6995bed17f9bc7d30d0555c58d3160e544d1fdc50805416d60

Observation 565a9be8-8fed-4b07-9a50-0097e79935ba · outbound

This paper cites Better Instruction-Following Through Minimum Bayes Risk.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Better Instruction-Following Through Minimum Bayes Risk

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.989399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.989399Z digest=sha256:dccdddc473ebb9122d6817804f3d0e5a3790a6ab534b198a52eb27354c0dc58b

Observation cab398a7-a96d-4353-8931-68902974348b · outbound

This paper cites an unresolved cited work.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-09T22:58:24.763608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-08-09T22:58:23.994450Z digest=sha256:197339de3d7adb66b26fd4bf99a58396447a4c69e297425a07520cbb03d0482d

Observation 5b01ea52-c767-4e6c-8d65-205ea98869a1 · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs When More is Less: Understanding Chain-of-Thought Length in LLMs

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:23.999177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:23.999177Z digest=sha256:3602323a0e0a43cce2e60a7d0aa04bc6f99ddefdb2c129033b7bcc8d05024b02

Observation 46e046e1-0b93-4ebf-bfbd-1c9ad06fe9a3 · outbound

This paper cites @esa (Ref.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs @esa (Ref

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:24.005276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:24.005276Z digest=sha256:505ac08e3ec5170d7fd33cc95bd26ecec80f098e1b00f60527627d7eb99f62c8

Observation 342c19fe-89e1-4d87-89ef-881d03970539 · outbound

This paper cites an unresolved cited work.

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:24.010203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:24.010203Z digest=sha256:c8f8e07d4424b6aa4edcc4e8c06e6c90091533c314b4212ead78860318da0f18

Observation cad152ea-f127-4ad2-abcc-8f618898fe14 · outbound

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

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-09T22:58:24.015239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T22:58:24.015239Z digest=sha256:880fe59ef1b0fd59ab869332351f6d540990eb4d4fc2a7315d2056d9cf278ede

Pith citing papers

Observation c1ca1916-90d6-425e-9400-bf4524171c3a · inbound

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

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 19

Resolution
metadata mismatch
arxiv_id, observed 2026-05-18T00:19:22.271647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-18T00:19:22.140009Z digest=sha256:917a4b62935eb449205b25a48b13c598ae0161217f8e60291b253a00004cbf33

Observation 1ce53576-c18e-4084-9cfa-4c77db04e93f · inbound

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding cites this paper.

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 22

Resolution
metadata mismatch
arxiv_id, observed 2026-05-17T19:21:42.179291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-17T19:21:42.081762Z digest=sha256:b0acfb3769c38f9f0b4515a79d65f77560f0addf3e75c5a90675916796a723d6

Observation 16b13ffb-070e-4886-8b05-98089c6139d2 · inbound

A Survey of Scaling in Large Language Model Reasoning cites this paper.

A Survey of Scaling in Large Language Model Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 213

Resolution
verified exact
arxiv_id, observed 2026-05-22T21:22:09.427634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-22T21:20:07.238992Z digest=sha256:16aa58dfb121be1063731bd385f66e1d924bcf167d5664da2e9e6096d683fbe1

Observation df0345db-cf64-4aab-a358-bd463743294f · inbound

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning cites this paper.

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T06:04:14.514628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T06:04:14.514628Z digest=sha256:e8f98a507c489282215e8670e7147f1221d7709f83ad7846b43784ae8ec98222

Observation c9585319-c872-4a0d-a53f-78748926bcc4 · inbound

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs cites this paper.

DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T22:29:45.414241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T22:29:45.414241Z digest=sha256:009632ffeb724189fe2901becec8cab43d5fde51695869eddfbfc0bd9c8d9794

Observation 1abcca14-fdfd-4358-aa5f-a7c0a848bebe · inbound

Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations cites this paper.

Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-15T21:07:08.157242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T21:07:08.157242Z digest=sha256:a1ceb0362bcc1e62d877e0f2faf0997f835b01be46c8991f15095326a999c844

Observation 2b493136-f030-405e-9e63-07ef4dafd25f · inbound

Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst cites this paper.

Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:22.738560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:22.738560Z digest=sha256:a7c9185780bc0de01edd5da6679f45097aa148ff356ab2f6fc9f16b74c777565

Observation c0db09e6-e810-44d4-abf1-02bfcfc35d30 · inbound

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training cites this paper.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T15:36:06.109851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:36:06.109851Z digest=sha256:a550876b8aae21ec2fe4b3dbc84a2adaa27267b5fd0ca4fa30c28cd1674c541d

Observation b6f8b0d4-7ab8-4cd1-8299-3f881701ac04 · inbound

Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems cites this paper.

Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-07T14:40:38.414916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:40:38.414916Z digest=sha256:56930f2ce0c33ac659866904015cdd5d27ee1efbd82b99d53fbaef984c2f5ea0

Observation 4fc7de80-569c-4865-9f02-3751b968a9cb · inbound

First Finish Search: Efficient Test-Time Scaling in Large Language Models cites this paper.

First Finish Search: Efficient Test-Time Scaling in Large Language Models Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-07T14:40:42.304124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:40:42.304124Z digest=sha256:6c9f07d64fc38301bcea3fb234c9f5c88cce3347aa27119e03a72f8d8b2a8fd2

Observation 347f68ce-03c9-4f35-8822-8f0f3d30ee45 · inbound

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning cites this paper.

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-07T13:20:13.072510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:20:13.072510Z digest=sha256:8252b4497c6b565ab2dba57b02a7d70fd76999c0832468529708f0127ec3671a

Observation 62524ee9-31ba-4b0c-8ff7-55363b19f075 · inbound

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time cites this paper.

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-07T12:35:45.024969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T12:35:45.024969Z digest=sha256:3e5bbfe2fda73045ccc2e7576b5857c7207b2ddf0edef1f7c930f5db742ca6b0

Observation 818b7f98-d39d-4f83-a94e-12c3116d8408 · inbound

Control-R: Towards controllable test-time scaling cites this paper.

Control-R: Towards controllable test-time scaling Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T12:14:21.099005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:14:21.099005Z digest=sha256:82ee4b84cbe65a09aa08043bb64ba9f81c4ac0e8400d77cae7d84904c4e2f82c

Observation 4f37b2ca-202f-4c65-a786-0e39b2586b8f · inbound

One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL cites this paper.

One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T11:30:40.358899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:30:40.358899Z digest=sha256:8bbd474bf44eeccb7ef21dc39e7da98e077dec32e4f40800833a56b937fc78b2

Observation ae340cfc-0fb0-4e3f-b81e-e73d7c2f251c · inbound

ReasoningFlow: Semantic Structure of Complex Reasoning Traces cites this paper.

ReasoningFlow: Semantic Structure of Complex Reasoning Traces Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T11:25:51.719097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T11:25:51.719097Z digest=sha256:1bc376544954df8b73f40aedc518f4ec490a5b126f1e92522c927dd859e201a6

Observation 02cac6bf-36c2-461b-b13f-783b4d571ac2 · inbound

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation cites this paper.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T10:52:49.599042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:52:49.599042Z digest=sha256:8db2633524ba41107846846f0b98edaa890aa849217b0b07538676bb496d0621

Observation efaa6c35-3461-45d9-8c86-d68e68440617 · inbound

Sample Complexity and Representation Ability of Test-time Scaling Paradigms cites this paper.

Sample Complexity and Representation Ability of Test-time Scaling Paradigms Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-07T10:35:39.099727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T10:35:39.099727Z digest=sha256:ea8c675c0bd472abf35b3be3cba59b4c71e520a85bb293110ec800b2ae61ffef

Observation 76841248-9d69-4b5e-b366-47d44e28e2b8 · inbound

Unlocking Recursive Thinking of LLMs: Alignment via Refinement cites this paper.

Unlocking Recursive Thinking of LLMs: Alignment via Refinement Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T06:07:02.104060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T06:07:02.104060Z digest=sha256:b00118a36efc9f73e65d0945e74a664de21992b5c94280576253583d9ce76900

Observation 9ab04672-346d-4d5f-9acc-3ac96ce57346 · inbound

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs cites this paper.

Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T05:45:05.947519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:45:05.947519Z digest=sha256:3c4c6f7d641c5ed8668fdd4edf00ac3f7b6c87630f8f5d7c48c93d99bdfd420a

Observation 5071db1e-a347-4308-b909-6cc07d7a0e06 · inbound

A Survey on Large Language Models for Mathematical Reasoning cites this paper.

A Survey on Large Language Models for Mathematical Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-07T05:14:47.493623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:14:47.493623Z digest=sha256:919125da54bf85b3888916b2de4b461d916e8a3f0f783fd979998bda69bc5f2a

Observation 18dac5ce-0d04-446d-9fa6-7808f1a8d6e6 · inbound

Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System cites this paper.

Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-07T05:04:05.615825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T05:04:05.615825Z digest=sha256:43a9ea81d293bc9ccffad8d5f3c2fdf8259bc7c0e63e2e4ff0367ffd4d1dafe8

Observation db5ace98-dfbb-46c7-bbb7-d387d65e5643 · inbound

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models cites this paper.

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T00:57:02.795577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:57:02.795577Z digest=sha256:55b5472cc90d32951e52efe5970bf24f8f05db2fc4d8ad8a909c57a013a63f06

Observation 410d4bae-04aa-4806-92f5-e0260bd428de · inbound

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning cites this paper.

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T20:13:19.506091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:13:19.506091Z digest=sha256:f5356df029b485c8e9083e64f612cd79585c81597bcd1d775c4231cc78d5014e

Observation 89a71b8c-33e4-4b5d-9d37-483a6a3c2083 · inbound

Excessive Reasoning Attack on Reasoning LLMs cites this paper.

Excessive Reasoning Attack on Reasoning LLMs Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T00:23:39.676722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:23:39.676722Z digest=sha256:1198f98d22634cb0fcdc1f351184a65b32ac0395e65333098bffb981984ba2b5

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

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model cites this paper.

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.

source=pdf_text observed=2026-08-06T23:28:40.224745Z digest=sha256:673ea9db1dda5fcf52e8f9b18957f6b00b38cb76da5b4f6a881774450d00e4c1

Observation f8962d96-f2f8-48e6-81d6-47e40e7fa886 · inbound

Towards Understanding the Cognitive Habits of Large Reasoning Models cites this paper.

Towards Understanding the Cognitive Habits of Large Reasoning Models Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-07T04:07:58.496937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:07:58.496937Z digest=sha256:157495245de9df72cc41a113e174871654f2e4dea36e026433680597d9fa6c0b

Observation 3dfce824-a629-46ca-9da1-2e4a08c2e132 · inbound

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model cites this paper.

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T21:45:10.787149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T21:45:10.787149Z digest=sha256:68ccbc7beb2d49cdc650b633da4e82cabbc48268b73ab1685cd2cf102bcb7e9a

Observation 0fd5dae3-0522-43a6-ac4b-fe8238e94796 · inbound

Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories cites this paper.

Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T21:13:13.046279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T21:13:13.046279Z digest=sha256:27c240fb1a80625a09d17ba1ba23e18cc62313a8c64cc6dfe73cedea48e726e9

Observation 013342ee-dd4c-4b41-96c8-ed271109e856 · inbound

HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision cites this paper.

HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T20:46:00.202834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:46:00.202834Z digest=sha256:ba14afd7908aee60cc88da9b204d58ed77d0d5b1e12a56de1546556c9e3afb2a

Observation 819b88e1-36a6-48b4-9ffe-d6c54456a1a6 · inbound

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks cites this paper.

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T20:43:25.974047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T20:43:25.974047Z digest=sha256:fe634fa79dc929b58aa2f0f40a428ca7e4f2e8b905b70df14a3d926210e7cdea

Observation a031feb2-6343-424f-a645-7b04a53d4087 · inbound

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs cites this paper.

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T20:43:10.721707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T20:43:10.721707Z digest=sha256:1d79121e615014e518e49392136610228da270311299618cde857c8eb4651e25

Observation 84f613c9-adcc-454d-bb6a-7d2b9e7735c4 · inbound

Activation Steering for Chain-of-Thought Compression cites this paper.

Activation Steering for Chain-of-Thought Compression Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T19:46:48.487783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T19:46:48.487783Z digest=sha256:40f5175e144c667a194bd1d11f361f4879f2387034b75b36807d1c4abbe0ac6b

Observation 4ca91113-fe53-4d02-939c-42191714b6a7 · inbound

Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework cites this paper.

Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T18:59:42.795443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:59:42.795443Z digest=sha256:15451612cc8aa1e1b64d58d5dc6fd5a56cf6fa6e97a69900297dedd7e0460e74

Observation be162794-7d48-431a-a5ed-730b9dd3f5e5 · inbound

OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique cites this paper.

OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T18:11:19.140195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T18:11:19.140195Z digest=sha256:0853fcbb7a2d348e56860fc60731ea8b80b3f215b4f5c75c0a1721d70fa83eaa

Observation df5bbf48-696d-48e1-ad0a-e5f70cfe8bd2 · inbound

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

REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-06T17:35:31.681214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T17:35:31.681214Z digest=sha256:a554ab940d8e12b1c5e82a28bc44f68b6d58aa1f7f5b31970dc94d7666ba7020

Observation 862812bc-f356-4f09-840b-3bab5c256cfe · inbound

It's Not That Simple. An Analysis of Simple Test-Time Scaling cites this paper.

It's Not That Simple. An Analysis of Simple Test-Time Scaling Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T16:09:06.009237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T16:09:06.009237Z digest=sha256:1fbcaae9319ad485260cafae2de34fa9820fbe547e06f53d967da2f5b6b65288

Observation e228e5ed-4276-4971-b943-3801b8bf9c36 · inbound

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization cites this paper.

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-06T15:29:43.738162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T15:29:43.738162Z digest=sha256:934a2ecd4fd662d683abdbc869250a790d081955c8da3eef913de0ad3201e338

Observation 16d1b131-1cad-4ef3-af57-de8cd3b37a28 · inbound

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning cites this paper.

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-06T05:14:37.252378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T05:14:37.252378Z digest=sha256:ac6dceb203b50fa40740fae381e9cc9da6c40cba2528e91028e01a467b1ed3ce

Observation 8858b52a-37b7-43a8-8586-e097cd95e7ea · inbound

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training cites this paper.

Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T05:08:10.807715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T05:08:10.807715Z digest=sha256:884461fe8e58e5936090d9c11a843b7c842f16b434745168a2a9c27c08a312c1

Observation efbf2d0c-a6d7-42af-9ff6-1ba1fa900137 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 199

Resolution
unresolved
no resolver link, observed 2026-08-05T10:39:07.434982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:39:07.434982Z digest=sha256:714b57b32f7b4e4d67caebf76aa0be5c2bf44969fb694b58c5abb0b0318e3a65

Observation b7423783-3728-459f-b13b-7afe4f5b43c7 · inbound

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains cites this paper.

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-05T00:04:02.000470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T00:04:02.000470Z digest=sha256:31a5d07828598c48e9488bb76258639450de08b097c7923c4ef5ad3c0f342c92

Observation cc9b02d1-103f-40fb-ad47-c20ca44699a8 · inbound

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering cites this paper.

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-03T12:21:00.941884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-03T12:21:00.941884Z digest=sha256:b6e81474bf3d9b2ac3aab4f8a484569596e20cd503db5c53b43833b729414929

Observation fba77e2f-f37f-4cff-a88c-76ec1fe3b22b · inbound

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems cites this paper.

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-03T05:31:40.145833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T05:31:40.145833Z digest=sha256:92940d26734b6be9e959b247b24e693acf2862361c3992d59fc874fee2520909

Observation 4b1d8c62-0939-46ca-8b88-4c06223128c4 · inbound

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 70

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:31:10.681902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-08T11:42:16.090162Z digest=sha256:03e0becb1c895288575a74261aabda857efd08dde8161745cccc050bf4157c67

Observation 055da550-b1f6-4eef-91dd-a17c0e9136f5 · inbound

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes cites this paper.

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 70

Resolution
verified exact
arxiv_id, observed 2026-05-14T19:27:52.091069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-05-14T19:25:07.440630Z digest=sha256:5e0a6341a12b42bb8243b96df64ad7696844cac5017fedf5c057fae495afb994

Observation bec559f3-81d6-4721-9079-f8adf5b6f043 · inbound

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning cites this paper.

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-05-20T22:54:09.624281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-20T22:54:04.159660Z digest=sha256:e1279c686b8ebbc4e19831e2770729b14b93f7be975021ff4d8c7eb4c7db4754

Observation d3a09fb8-91de-4e93-8218-508a8273375e · inbound

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning cites this paper.

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-06-30T22:45:07.204877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-30T22:44:41.528444Z digest=sha256:57c6dff457b97b31bb72d19ec03b80a274b264d8ccac37b4a2786beaba25c8ab

Observation b1ff0663-24b1-4806-98f0-d4e265ece276 · inbound

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning cites this paper.

PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 60

Resolution
verified exact
arxiv_id, observed 2026-05-25T05:25:23.716859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-05-25T05:22:08.579832Z digest=sha256:ffa0874f9f4c10e99f7d9aa21c042884b60be83b66aaa7613fb14636f2b9b42e

Observation 24b7c06b-859c-4b0e-ab82-3b3bd500b236 · inbound

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning cites this paper.

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 58

Resolution
verified exact
arxiv_id, observed 2026-06-29T12:03:23.704157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-06-29T12:02:14.499758Z digest=sha256:4a5eb9c412ae67b374cba20dab3f17a8dffa5f7dfb7407abd7f33d3e6f83ddc3

Observation ece1afe0-4737-489b-b4ee-4636b0bf1063 · inbound

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes cites this paper.

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 248

Resolution
verified exact
arxiv_id, observed 2026-07-03T05:57:41.556657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-27T12:59:51.091008Z digest=sha256:db5a97c15033fa0c5b839bebae6a2aa47498a1d1e06a4dae193aa990cbcde84f

Observation 3a16201a-63d9-48dc-9871-63fe26013065 · inbound

SuCo: Sufficiency-guided Continuous Adaptive Reasoning cites this paper.

SuCo: Sufficiency-guided Continuous Adaptive Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 87

Resolution
verified exact
arxiv_id, observed 2026-07-03T21:08:58.565977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-06-27T00:52:48.590168Z digest=sha256:d55b46dc33ed82c60100eb0dd0e6c5072a0ef13f608f8ff5c560f665a9f63e6c

Observation 6e37a9de-f2bf-488c-ad8c-b2458d6de9d8 · inbound

Addressing Over-Refusal in LLMs with Competing Rewards cites this paper.

Addressing Over-Refusal in LLMs with Competing Rewards Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 13

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T07:05:29.280514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-07-01T06:59:12.695984Z digest=sha256:5039d7dab2624e41bb3a28288428286897a8c072c9afe0da2bed1b00aae744f5

Observation abab6172-4711-4ee2-ae87-abe4c3fad19c · inbound

Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking cites this paper.

Know When to Stop: Segment-Level Credit Assignment for Reducing Overthinking Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 84

Resolution
verified exact
arxiv_id, observed 2026-07-02T13:36:58.577286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-07-02T13:31:40.676016Z digest=sha256:4291e4840835b4ad5f06143bb6565084ade052074a1f300d810bddf7a9690ce6

Observation 11e8be67-a942-48b9-8974-27573077a593 · inbound

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models cites this paper.

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-07-02T13:26:58.109980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=arxiv_source observed=2026-07-02T13:22:27.566432Z digest=sha256:f30087932a3f986ee688657acf3ada71fef9ec442a12c1f12e70bfe048ce2157

Observation 2bd2aeb4-b9d2-4763-afb8-2cc0dfc57358 · inbound

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning cites this paper.

CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T10:48:09.743438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:48:09.743438Z digest=sha256:b0f335d8c9bbf2e8a0d9d36b477d71556d016d08b584fd12207b43ff7fecc80a