Tool-Integrated Reasoning

Latest papers

11 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
Aug 22, 2026Yucan Guo, Xiaohan Wang, Miao Su +8Tool-Integrated Reasoning Credit Assignment
State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Aug 4, 2026Changle Qu, Sunhao Dai, Hengyi Cai +4Tool-Integrated Reasoning On-Policy Self-Distillation
Gaoling School of Artificial Intelligence, Renmin University of China · Baidu Inc.
QueryWeaver: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation
Jun 6, 2026Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng ChauTool-Augmented Language Model Agents Tool-Use Planning
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA.
DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
May 28, 2026Yang He, Xiao Ding, Bibo Cai +5Reinforcement Learning Tool-Integrated Reasoning
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, China
Knowing When to Ask: Segment-Level Credit Assignment for LLM Tool Use
May 27, 2026Abhijit Kumar, Zoey Wu, Mohit SuleyRL for LLM Agents Reward Design for RL
Microsoft AI Redmond, WA
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
May 11, 2026Luan Zhang, Dandan Song, Zhijing Wu +8LLM Inference Efficiency Tool-Integrated Reasoning
School of Computer Science and Technology, Beijing Institute of Technology, China · 3Independent, China · School of Computer Science and Technology, Huazhong University of Science and Technology, China
SOD: Step-wise On-policy Distillation for Small Language Model Agents
May 8, 2026Qiyong Zhong, Mao Zheng, Mingyang Song +5Tool-Integrated Reasoning LLM Agent Training
1Zhejiang University · 2Large Language Model Department, Tencent · University of Science and Technology of China +1
Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
May 7, 2026Qianjia Cheng, Yuchen Zhang, Zhilin Wang +9Tool-Integrated Reasoning RL for Language Model Reasoning
Zhejiang University · Shanghai AI Laboratory · Peking University +4
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning
Apr 10, 2026Weiyang Guo, Zesheng Shi, Liye Zhao +5Tool-Integrated Reasoning LLM Agent Training
Harbin Institute of Technology, Shenzhen, China · Huawei Technologies Co., Ltd. · Hong Kong University of Science and Technology
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
Apr 9, 2026Ruotao Xu, Yixin Ji, Yu Luo +5Tool-Integrated Reasoning LLM Reasoning
School of Computer Science and Technology, Soochow University · Department of Foundation Model, 2012 Labs, Huawei · Harbin Institute of Technology, Shenzhen (HITSZ)
Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning
Sep 27, 2025Ningning Xu, Yuxuan Jiang, Shubhashis Roy Dipta +1Tool-Integrated Reasoning LLM Tool Use
University of Georgia · University of Maryland, Baltimore County · 3The University of Hong Kong

Aug 22, 2026J/K move · Enter open · S save

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning

Yucan Guo, Xiaohan Wang, Miao Su, Saiping Guan+7

State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences+1

Tool-Integrated Reasoning Credit Assignment RL for LLM Agents RL for Tool Use

Open paper AskPDF arXiv

Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has become the dominant paradigm for enabling this capability. However, existing approaches typically assign uniform trajectory-level advantages and treat all correct tool calls equally, ignoring the varying difficulty and learning value across trajectories and reasoning steps. This can lead to imprecise learning signals that do not adequately distinguish between trivial and challenging tool-use patterns. To address this limitation, we propose HiDiffTIR, a Hierarchical Difficulty-aware policy optimization framework for multi-turn TIR. HiDiffTIR performs difficulty-aware credit assignment at both trajectory and turn levels, enabling the policy to focus on more informative trajectories and harder reasoning steps. Notably, this fine-grained optimization is achieved without additional supervision, relying solely on group-level statistics derived from standard RL rollouts. Extensive experiments on three tool-using benchmarks demonstrate that HiDiffTIR consistently improves multi-turn TIR performance and tool invocation accuracy over strong RL baselines, highlighting the necessity of difficulty-aware credit assignment for effective policy optimization in tool-integrated LLM agents.