English
Related papers

Related papers: E3-TIR: Enhanced Experience Exploitation for Tool-…

200 papers

Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explicit reasoning process to achieve better performance. However, there are some key…

Artificial Intelligence · Computer Science 2026-03-17 Yirong Zeng , Xiao Ding , Yufei Liu , Yuxian Wang , Qunyao Du , Yutai Hou , Wu Ning , Haonan Song , Duyu Tang , Dandan Tu , Bing Qin , Ting Liu

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…

Machine Learning · Computer Science 2025-08-28 Zhiwei Li , Yong Hu , Wenqing Wang

Reasoning large language models (LLMs) excel in complex tasks, which has drawn significant attention to reinforcement learning (RL) for LLMs. However, existing approaches allocate an equal number of rollouts to all questions during the RL…

Machine Learning · Computer Science 2025-10-21 Mengqi Liao , Xiangyu Xi , Ruinian Chen , Jia Leng , Yangen Hu , Ke Zeng , Shuai Liu , Huaiyu Wan

Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, referred to as ETO. This learning method is designed to…

Computation and Language · Computer Science 2024-07-11 Yifan Song , Da Yin , Xiang Yue , Jie Huang , Sujian Li , Bill Yuchen Lin

Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. Inspired by human…

Artificial Intelligence · Computer Science 2026-02-17 Qianyue Wang , Jinwu Hu , Huanxiang Lin , Bolin Chen , Zhiquan Wen , Yaofo Chen , Yu Rong , Mingkui Tan

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

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…

Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit…

Computation and Language · Computer Science 2026-02-11 Qiao Liang , Yuke Zhu , Chao Ge , Lei Yang , Ying Shen , Bo Zheng , Sheng Guo

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…

Machine Learning · Computer Science 2026-02-06 Zhenning Shi , Yijia Zhu , Junhan Shi , Xun Zhang , Lei Wang , Congcong Miao

Entity Linking (EL) has traditionally relied on large annotated datasets and extensive model fine-tuning. While recent few-shot methods leverage large language models (LLMs) through prompting to reduce training requirements, they often…

Computation and Language · Computer Science 2025-11-20 Yajie Li , Albert Galimov , Mitra Datta Ganapaneni , Pujitha Thejaswi , De Meng , Priyanshu Kumar , Saloni Potdar

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Machine Learning · Computer Science 2026-04-02 Marc-Antoine Allard , Arnaud Teinturier , Victor Xing , Gautier Viaud

Training Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR) - where models iteratively reason, generate code, and verify through execution - remains challenging for existing reinforcement learning (RL) approaches.…

Machine Learning · Computer Science 2026-04-21 Yifeng Ding , Hung Le , Songyang Han , Kangrui Ruan , Zhenghui Jin , Varun Kumar , Zijian Wang , Anoop Deoras

Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent studies focus on exploring various methods to equip LLMs with…

Computation and Language · Computer Science 2026-05-12 Luan Zhang , Dandan Song , Zhijing Wu , Zhengyu Chen , Chen Zhang , Yuhang Tian , Huipeng Ma , Chenhao Li , Changzhi Zhou , Xudong Li , Shuhao Zhang

Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods benefit from diverse…

Machine Learning · Computer Science 2026-05-12 Changhao Li , Yuchen Zhuang , Chenxiao Gao , Haotian Sun , Rushi Qiang , Chao Zhang , Bo Dai

While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where…

Computation and Language · Computer Science 2026-04-21 Ziliang Wang , Kang An , Xuhui Zheng , Faqiang Qian , Weikun Zhang , Cijun Ouyang , Jialu Cai , Yuhang Wang , Yichao Wu

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks, sparking growing interest in their application to preference reasoning in recommendation systems. Existing methods typically…

Artificial Intelligence · Computer Science 2025-10-27 Yang Zhang , Wenxin Xu , Xiaoyan Zhao , Wenjie Wang , Fuli Feng , Xiangnan He , Tat-Seng Chua

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many…

Databases · Computer Science 2021-11-23 Yu Yan , Hongzhi Wang , Jian Ma , Jian Geng , Yuzhuo Wang

Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly studied when to invoke tools, while overlooking how tools are applied. We identify two common…

Artificial Intelligence · Computer Science 2026-01-12 Ningning Xu , Yuxuan Jiang , Shubhashis Roy Dipta , Hengyuan Zhang

As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts…

Artificial Intelligence · Computer Science 2025-10-30 Zekun Xu , Siyu Xia , Chuhuai Yue , Jiajun Chai , Mingxue Tian , Xiaohan Wang , Wei Lin , Haoxuan Li , Guojun Yin

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Computation and Language · Computer Science 2025-10-10 Jing Li , Zhijie Sun , Dachao Lin , Xuan He , Binfan Zheng , Yi Lin , Rongqian Zhao , Xin Chen