English
Related papers

Related papers: ASTER: Agentic Scaling with Tool-integrated Extend…

200 papers

Large reasoning models (LRMs) achieve state-of-the-art performance by generating long chains-of-thought, but often waste computation on redundant reasoning after the correct answer has already been reached. We introduce Early-Stopping for…

Artificial Intelligence · Computer Science 2026-02-11 Junda Wang , Zhichao Yang , Dongxu Zhang , Sanjit Singh Batra , Robert E. Tillman

We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such as thinking…

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

Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they remain insufficient for agentic settings, where actions directly interact with…

Computation and Language · Computer Science 2026-02-04 Xingshan Zeng , Lingzhi Wang , Weiwen Liu , Liangyou Li , Yasheng Wang , Lifeng Shang , Xin Jiang , Qun Liu

Tool-Integrated Reasoning (TIR) has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools during reasoning. Existing TIR methods typically rely on external tool documentation during…

Computation and Language · Computer Science 2026-04-14 Qiancheng Xu , Yongqi Li , Fan Liu , Hongru Wang , Min Yang , Wenjie Li

Large Language Models (LLMs) have achieved strong performance on static reasoning benchmarks, yet their effectiveness as interactive agents operating in adversarial, time-sensitive environments remains poorly understood. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Yang Li , Xing Chen , Yutao Liu , Gege Qi , Yanxian BI , Zizhe Wang , Yunjian Zhang , Yao Zhu

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is…

Artificial Intelligence · Computer Science 2025-04-11 Fu-Chieh Chang , Yu-Ting Lee , Hui-Ying Shih , Yi Hsuan Tseng , Pei-Yuan Wu

Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools during long-form reasoning, such as search engines and code interpreters, to solve tasks beyond the capabilities of internal…

Artificial Intelligence · Computer Science 2025-06-03 Hongru Wang , Cheng Qian , Wanjun Zhong , Xiusi Chen , Jiahao Qiu , Shijue Huang , Bowen Jin , Mengdi Wang , Kam-Fai Wong , Heng Ji

Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex…

Machine Learning · Computer Science 2026-05-18 Haizhong Zheng , Yizhuo Di , Jiahui Wang , Shuowei Jin , Xueshen Liu , Yongji Wu , Z. Morley Mao , Ion Stoica , Jiawei Zhao , Beidi Chen

Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments LLMs with external tools to enable agentic reasoning, achieving high utility and efficiency in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Qi Li , Xinchao Wang

Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress. While "aha moment" patterns--where models…

Computation and Language · Computer Science 2025-07-24 Lai Wei , Yuting Li , Kaipeng Zheng , Chen Wang , Yue Wang , Linghe Kong , Lichao Sun , Weiran Huang

Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, its training is often plagued by \emph{entropy collapse}, a rapid…

Machine Learning · Computer Science 2026-04-30 Zhezheng Hao , Hong Wang , Haoyang Liu , Jian Luo , Jiarui Yu , Hande Dong , Qiang Lin , Can Wang , Jiawei Chen

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Computation and Language · Computer Science 2026-02-05 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Guojun Yin , Wei Lin , Ran He

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

Large Language Models (LLMs) can significantly improve their reasoning capabilities by interacting with external tools, a paradigm known as Tool-Integrated Reasoning (TIR). However, extending TIR to multi-turn scenarios using Reinforcement…

Machine Learning · Computer Science 2025-09-04 Zhenghai Xue , Longtao Zheng , Qian Liu , Yingru Li , Xiaosen Zheng , Zejun Ma , Bo An

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

Computation and Language · Computer Science 2025-12-15 Mrinal Rawat , Arkajyoti Chakraborty , Neha Gupta , Roberto Pieraccini

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL…

Artificial Intelligence · Computer Science 2026-05-29 Yang He , Xiao Ding , Bibo Cai , Yufei Zhang , Kai Xiong , Zhouhao Sun , Bing Qin , Ting Liu

We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL allows models to…

Computation and Language · Computer Science 2025-04-01 Xuefeng Li , Haoyang Zou , Pengfei Liu

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

Artificial Intelligence · Computer Science 2026-05-05 Caijun Xu , Changyi Xiao , Zhongyuan Peng , Xinrun Wang , Yixin Cao