Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer? We bring two lines of evidence to bear. First, in distribution: we repeatedly sample each model on the same question and pair a shorter with a longer of its own natural generations that follow the same reasoning plan, so nothing is rewritten and both traces are genuinely in-distribution. Across 25 models the extra tokens leave accuracy essentially unchanged for every independently-trained reasoner, and a blind analysis of the surplus tokens shows that what gain exists elsewhere tracks validation- and checking-content, not verbosity per se. Second, as a controlled intervention, we ask whether two traces expressing the same semantic content (the same facts, operations, and intermediate values, verified through directed acyclic graph equivalence) produce different outcomes when one is more verbose, using a dual-validator design across four targets and eight benchmarks with number-redacted completion and stratified bootstrap confidence intervals. Verbose traces do improve accuracy (25 of 32 benchmark-target cells are positive under at least one validator), but the effects are modest (typically 1-4 points) and depend on the quality of the verbose prose, not merely its length. Under maximum numerical redaction the effect is amplified (median 3.24x across four arithmetic benchmarks), and length-matched non-reasoning filler recovers none of it. Both lines converge: what matters is what the extra tokens do (the reasoning and validation content they carry), not how many there are, a picture neither a pure forward-pass-compute nor a pure semantic-content account fully explains.
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo(宁波数字孪生研究院,东方理工高等研究院,宁波);Viterbi School of Engineering, University of Southern California(南加州大学维特比工程学院);The Hong Kong Polytechnic University(香港理工大学);LMU Munich(慕尼黑大学);Saarland University(萨尔大学)
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Baidu Inc.(百度公司);Tencent Inc.(腾讯公司)
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
IIIS, Tsinghua University(清华大学信息学院);Shanghai Qi Zhi Institute(上海启智研究院);Department of Statistics and Data Science, University of Pennsylvania(宾夕法尼亚大学统计与数据科学系);Data Agent Group, Beijing Academy of Artificial Intelligence(北京人工智能研究院数据代理组)
SEER: Self-Enhancing Chain-of-Thought Compression for Reasoning Models
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);State Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学)
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
School of New Media and Communication, Tianjin University(新媒体与传播学院,天津大学);School of Computer Science and Engineering, Beihang University(计算机科学与工程学院,北航大学)
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波数字孪生研究院,东方理工大学);Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学系)
Do Efficient Transformers Really Save Computation?
School of EECS, Peking University(北京大学信息与工程科学学院(电子工程与计算机科学学院));ETH Zürich(苏黎世联邦理工学院);National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(北京大学通用人工智能重点实验室、智能科学与技术学院);New York University(纽约大学);Beijing Academy of Artificial Intelligence(北京智源人工智能研究院);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心)
Can multiple-choice questions really be useful in detecting the abilities of LLMs?
Meetyou AI Lab(MeetYou人工智能实验室);Southwestern University of Finance and Economics(西南财经大学);Osaka University(大阪大学);Chongqing University of Posts and Telecommunications(重庆邮电大学)
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学);National University of Singapore(新加坡国立大学);Zhongguancun Academy(中关村学院)