English
Related papers

Related papers: Implicit Hierarchical GRPO: Decoupling Tool Invoca…

200 papers

Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However,…

Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential.…

Artificial Intelligence · Computer Science 2026-02-10 Aditya Basarkar , Benyamin Tabarsi , Tiffany Barnes , Dongkuan Xu

Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the…

Mathematical reasoning tasks have become prominent benchmarks for assessing the reasoning capabilities of LLMs, especially with reinforcement learning (RL) methods such as GRPO showing significant performance gains. However, accuracy…

Artificial Intelligence · Computer Science 2025-05-30 Tian Qin , Core Francisco Park , Mujin Kwun , Aaron Walsman , Eran Malach , Nikhil Anand , Hidenori Tanaka , David Alvarez-Melis

Inference scaling further accelerates Large Language Models (LLMs) toward Artificial General Intelligence (AGI), with large-scale Reinforcement Learning (RL) to unleash long Chain-of-Thought reasoning. Most contemporary reasoning approaches…

Machine Learning · Computer Science 2025-05-20 Xuerui Su , Liya Guo , Yue Wang , Yi Zhu , Zhiming Ma , Zun Wang , Yuting Liu

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to…

Software Engineering · Computer Science 2025-06-04 Mingzhe Du , Luu Anh Tuan , Yue Liu , Yuhao Qing , Dong Huang , Xinyi He , Qian Liu , Zejun Ma , See-kiong Ng

The effective training of Large Language Models (LLMs) for function calling faces a critical challenge: balancing exploration of complex reasoning paths with stable policy optimization. Standard methods like Supervised Fine-Tuning (SFT)…

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning,…

Artificial Intelligence · Computer Science 2026-05-29 Siyao Song , Cong Ma , Zhihao Cheng , Shiye Lei , Minghao Li , Ying Zeng , Huaixiao Tou , Kai Jia

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as…

Artificial Intelligence · Computer Science 2025-12-04 Boyang Gu , Hongjian Zhou , Bradley Max Segal , Jinge Wu , Zeyu Cao , Hantao Zhong , Lei Clifton , Fenglin Liu , David A. Clifton

Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). However, existing studies mainly focus on enabling models to perform tool invocation, while…

Computation and Language · Computer Science 2026-05-20 Qinghe Ma , Zhen Zhao , Yiming Wu , Jian Zhang , Lei Bai , Yinghuan Shi

In real-world Tool-Integrated Reasoning (TIR) scenarios, where LLMs interleave reasoning with external tool calls, a major source of inefficiency is that the toolcalls create pauses between LLM requests and cause KV-Cache eviction, forcing…

Performance · Computer Science 2026-04-15 Qisheng Su , Shiting Huang , Zhen Fang , Ziyan Chen , Zehui Chen , Feng Zhao

When applying reinforcement learning--typically through GRPO--to large vision-language model reasoning struggles to effectively scale reasoning length or generates verbose outputs across all tasks with only marginal gains in accuracy. To…

Computation and Language · Computer Science 2025-10-24 Wenyi Xiao , Leilei Gan

Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsistencies that standard outcome-based supervision fails to…

Artificial Intelligence · Computer Science 2026-01-01 Peng Kuang , Xiangxiang Wang , Wentao Liu , Jian Dong , Kaidi Xu

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents…

Artificial Intelligence · Computer Science 2025-08-21 Xinji Mai , Haotian Xu , Zhong-Zhi Li , Xing W , Weinong Wang , Jian Hu , Yingying Zhang , Wenqiang Zhang

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning…

Machine Learning · Computer Science 2025-03-31 Zhiyuan Liu , Yuting Zhang , Feng Liu , Changwang Zhang , Ying Sun , Jun Wang

Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…

Computation and Language · Computer Science 2026-01-27 Wengao Ye , Yan Liang , Lianlei Shan

Enhancing the mathematical reasoning of Large Language Models (LLMs) is a pivotal challenge in advancing AI capabilities. While Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are the dominant training paradigms, a systematic…

Machine Learning · Computer Science 2025-07-14 Hiroshi Yoshihara , Taiki Yamaguchi , Yuichi Inoue

Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code execution. However, this interleaved setup has three key…

Computation and Language · Computer Science 2026-05-12 Hyeon Hwang , Jiwoo Lee , Jaewoo Kang

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, understanding and validating their knowledge utilization remains challenging. Chain-of-thought (CoT) prompting partially addresses this by revealing…

Computation and Language · Computer Science 2025-02-06 Aissatou Diallo , Antonis Bikakis , Luke Dickens , Anthony Hunter , Rob Miller
‹ Prev 1 4 5 6 7 8 10 Next ›