arXiv AI July 8, 2026 By Marthe Ballon, Andres Algaba, Vincent Ginis

The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer

arXiv:2502. 15631v2 Announce Type: replace-cross Abstract: Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and reinforcement learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 7

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

The paper surveys efficient reasoning in large language models, contrasting fast intuitive (System 1) and slow deep (System 2) reasoning. It analyzes why System 2 is computationally costly yet more accurate, and why System 1 is efficient but less effective. The survey covers causes of inefficiency, patterns of reasoning behavior, and potential solutions to balance performance and computational budgets, offering actionable insights and an open‑source repository for ongoing research.

By Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong

llms

arXiv AI

Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong

llms benchmarks

arXiv AI

Sep 25

To Think or Not to Think: Allocating Reasoning Where It Helps

The paper introduces CARE, a contrastive accuracy reward estimation method that adaptively adjusts reasoning length for large language models. By comparing beneficial length adjustments from online sampled responses, CARE applies adaptive length rewards within Group Relative Policy Optimization without extra hyperparameters or inference cost. Experiments on multiple reasoning benchmarks show that CARE improves Pass@1 by up to 4% while reducing reasoning length by 37%, achieving higher token efficiency.

By Zhengdong He, Yunfan Zhou, Jianguo Yao, Haibing Guan, Xijun Li

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

OckBench: Measuring the Efficiency of LLM Reasoning

arXiv:2511. 05722v3 Announce Type: replace-cross Abstract: Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation.

By Zheng Du, Hao Kang, Song Han, Tushar Krishna, Ligeng Zhu

llms benchmarks

arXiv AI

Jul 21

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs

arXiv:2510. 22228v2 Announce Type: replace-cross Abstract: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).

By Keyu Wang, Tian Lyu, Guinan Su, Lu Yin, Marco Canini, Jonas Geiping, Shiwei Liu

llms fine-tuning efficiency benchmarks

arXiv AI

Sep 15

Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost

arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...

By Richmond Sin Jing Xuan, Rishabh Bhardwaj, Soujanya Poria

llms efficiency benchmarks

One email a morning, machine-written

Related stories

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Fractured Chain-of-Thought Reasoning

To Think or Not to Think: Allocating Reasoning Where It Helps

OckBench: Measuring the Efficiency of LLM Reasoning

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs

Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost