English
Related papers

Related papers: InCoder-32B-Thinking: Industrial Code World Model …

200 papers

Complex chart understanding tasks demand advanced visual recognition and reasoning capabilities from multimodal large language models (MLLMs). However, current research provides limited coverage of complex chart scenarios and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Duo Xu , Hao Cheng , Xin Lin , Zhen Xie , Hao Wang

Chain-of-Thought (CoT) plays a crucial role in reasoning for math problem solving. We conduct a comprehensive examination of methods for designing CoT, comparing conventional natural language CoT with various program CoTs, including the…

Computation and Language · Computer Science 2023-10-03 Zhanming Jie , Trung Quoc Luong , Xinbo Zhang , Xiaoran Jin , Hang Li

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

Computation and Language · Computer Science 2026-03-25 Richard J. Young

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

Computation and Language · Computer Science 2025-06-30 James Chua , Edward Rees , Hunar Batra , Samuel R. Bowman , Julian Michael , Ethan Perez , Miles Turpin

Chain of Thought (CoT) prompting improves the reasoning performance of large language models (LLMs) by encouraging step by step thinking. However, CoT-based methods depend on intermediate reasoning steps, which limits scalability and…

Artificial Intelligence · Computer Science 2025-06-02 Guanghao Li , Wenhao Jiang , Mingfeng Chen , Yan Li , Hao Yu , Shuting Dong , Tao Ren , Ming Tang , Chun Yuan

Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…

Software Engineering · Computer Science 2026-03-25 Md Mahbubur Rahman , Hengbo Tong , Wei Le

Intermediate token generation (ITG), where a model produces output before the solution, has been proposed as a method to improve the performance of language models on reasoning tasks. While these reasoning traces or Chain of Thoughts (CoTs)…

Artificial Intelligence · Computer Science 2025-09-10 Vardhan Palod , Karthik Valmeekam , Kaya Stechly , Subbarao Kambhampati

Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from critical limitations in code generation, where upfront…

Software Engineering · Computer Science 2026-04-28 Xue Jiang , Tianyu Zhang , Ge Li , Mengyang Liu , Taozhi Chen , Zhenhua Xu , Binhua Li , Wenpin Jiao , Zhi Jin , Yongbin Li , Yihong Dong

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine Learning · Computer Science 2025-10-10 Yeskendir Koishekenov , Aldo Lipani , Nicola Cancedda

Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited their adoption. We identify a core latent instability issue…

Computation and Language · Computer Science 2025-09-26 Xilin Wei , Xiaoran Liu , Yuhang Zang , Xiaoyi Dong , Yuhang Cao , Jiaqi Wang , Xipeng Qiu , Dahua Lin

Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. While current researches continue to explore the benefits…

Computation and Language · Computer Science 2025-10-14 Wenkai Yang , Shuming Ma , Yankai Lin , Furu Wei

Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the…

Computation and Language · Computer Science 2024-12-17 Yu Kang , Xianghui Sun , Liangyu Chen , Wei Zou

Large language models (LLMs) have showcased remarkable prowess in code generation. However, automated code generation is still challenging since it requires a high-level semantic mapping between natural language requirements and codes. Most…

Computation and Language · Computer Science 2023-10-24 Yingwei Ma , Yue Yu , Shanshan Li , Yu Jiang , Yong Guo , Yuanliang Zhang , Yutao Xie , Xiangke Liao

Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…

Computation and Language · Computer Science 2025-04-28 Seunghyun Yoo

We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCode trains a reasoning model in two stages: (i) Rule…

Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning before producing a final answer. While LCoTs have enabled…

Artificial Intelligence · Computer Science 2025-05-29 Gangwei Jiang , Yahui Liu , Zhaoyi Li , Qi Wang , Fuzheng Zhang , Linqi Song , Ying Wei , Defu Lian

Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suffer from superficial pattern matching and causal opacity. In…

Machine Learning · Computer Science 2026-02-03 Haolin Pan , Lianghong Huang , Jinyuan Dong , Mingjie Xing , Yanjun Wu

With the increasing adoption of large language models (LLMs) in software engineering, the Chain of Thought (CoT) reasoning paradigm has become an essential approach for automated code repair. However, the explicit multi-step reasoning in…

Software Engineering · Computer Science 2025-06-02 Junwei Hu , Weicheng Zheng , Yihan Liu , Yan Liu

Reasoning-capable language models achieve state-of-the-art performance in diverse complex tasks by generating long, explicit Chain-of-Thought (CoT) traces. While recent works show that base models can acquire such reasoning traces via…

Chain-of-thought (CoT) decoding enables language models to improve reasoning performance at the cost of high generation latency in decoding. Recent proposals have explored variants of contemplation tokens, a term we introduce that refers to…

Computation and Language · Computer Science 2024-12-18 Jeffrey Cheng , Benjamin Van Durme