paper-with-me

홈 › Papers

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

2026-04-15 · Sumeet Ramesh Motwani, Daniel Nichols, Charles London, Peggy Li, Fabio Pizzati, Acer Blake, Hasan Hammoud, Tavish McDonald, Akshat Naik, Alesia Ivanova, Vignesh Baskaran, Ivan Laptev, Ruben Glatt, Tal Ben-Nun, Philip Torr, Natasha Jaques, Ameya Prabhu, Brian Bartoldson, Bhavya Kailkhura, Christian Schroeder de Witt arxiv

As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a scalable benchmark of 2,500 expert-designed problems spanning chemistry, mathematics, computer science, chess, and logic to isolate and directly measure the long-horizon CoT reasoning capabilities of frontier models. Problems consist of a short input with a verifiable answer; solving them requires navigating a graph of interdependent steps that span tens to hundreds of thousands of reasoning tokens. Each local step is individually tractable for frontier models, so failures reflect long-horizon reasoning limitations. At release, the best models achieve <10% accuracy (GPT 5.2: 9.8%; Gemini 3 Pro: 6.1%) on LongCoT, revealing a substantial gap in current capabilities. Overall, LongCoT provides a rigorous measure of long-horizon reasoning, tracking the ability of frontier models to reason reliably over extended periods.

📄 PDF Abstract BibTeX arXiv:2604.14140

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation

2025-02-06 · Bo Pang, Hanze Dong, Jiacheng Xu, Silvio Savarese 외

Large language models (LLMs), such as o1 from OpenAI, have demonstrated remarkable reasoning capabilities. o1 generates a long chain-of-thought (LongCoT) before answering a question. LongCoT allows LLMs to analyze proble…

In-Context LearningKnowledge DistillationMath

The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning

2025-10-08 · Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad, Sarath Chandar 외 arxiv

Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment", where the state is the prompt plus al…

Reinforcement Learning

SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration

2025-10-22 · Xichen Zhang, Sitong Wu, Haoru Tan, Shaozuo Yu 외 arxiv

The long chain-of-thought (LongCoT) capability is central to the recent breakthroughs achieved by large language models in complex reasoning tasks. However, the accompanying issue of ''underthinking'', where models exhib…

Mathematical Reasoning

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

2024-03-08 · ZiHao Wang, Anji Liu, Haowei Lin, Jiaqi Li 외

We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely m…

Code GenerationHallucinationInformation RetrievalMathematical Reasoning+2

LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning

2026-08-13 · Yupan Ding, Jing Xiao, Zhenyuan Zhang, Chaofeng Chen 외 arxiv

Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer future from extended image sequences. However, existin…

Spatial Reasoning