Cover Image

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Li, Wang, Xiaohan, Lu, Xiaodong, Zhang, Zipeng, Wu, Jinyang, Chai, Jiajun, Lin, Wei, Yin, Guojun
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AWPO: Enhancing Tool-Use of Large Language Models through Adaptive Integration of Reasoning Rewards
by: Lin, Zihan, et al.
Published: (2025)

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
by: Lin, Zihan, et al.
Published: (2025)

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
by: Lin, Zihan, et al.
Published: (2026)

When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
by: Wang, Li, et al.
Published: (2026)

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
by: Zhu, Dongsheng, et al.
Published: (2025)

Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval
by: Chen, Yanfei, et al.
Published: (2024)

MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
by: Xu, Zekun, et al.
Published: (2025)

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
by: Chang, Qikai, et al.
Published: (2025)

Advancing and Benchmarking Personalized Tool Invocation for LLMs
by: Huang, Xu, et al.
Published: (2025)

Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
by: Liu, Yilong, et al.
Published: (2026)

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
by: Lu, Yifei, et al.
Published: (2025)

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
by: Chen, Xiwen, et al.
Published: (2025)

Rethinking Personalization in Large Language Models at the Token Level
by: Zhang, Chenheng, et al.
Published: (2026)

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
by: Liu, Yanming, et al.
Published: (2026)

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
by: Song, Da, et al.
Published: (2026)

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
by: Mou, Yutao, et al.
Published: (2026)

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
by: Xia, Siyu, et al.
Published: (2025)

Are Full Rollouts Necessary for On-Policy Distillation?
by: Zhang, Yaocheng, et al.
Published: (2026)

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
by: Cheng, Qianjia, et al.
Published: (2026)

$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
by: Zhang, Yaocheng, et al.
Published: (2026)

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
by: Zou, Jiaru, et al.
Published: (2025)

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
by: Wang, Zhichao
Published: (2025)

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
by: Xu, Ruotao, et al.
Published: (2026)

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
by: Gou, Zhibin, et al.
Published: (2023)

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
by: Wu, Jinyang, et al.
Published: (2026)

RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
by: Liu, Xiao, et al.
Published: (2025)

OpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
by: Qiu, Zipeng
Published: (2025)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
by: Dai, Yanqi, et al.
Published: (2026)

Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning
by: Zhang, Hang, et al.
Published: (2026)

Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
by: Wu, Shengguang, et al.
Published: (2025)

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
by: Fu, Yuqian, et al.
Published: (2025)

Tool-Augmented Reward Modeling
by: Li, Lei, et al.
Published: (2023)

Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
by: Pang, Renning, et al.
Published: (2026)

MetaTool: Facilitating Large Language Models to Master Tools with Meta-task Augmentation
by: Wang, Xiaohan, et al.
Published: (2024)

ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers
by: Sengupta, Saptarshi, et al.
Published: (2025)

ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs
by: Chen, Hao, et al.
Published: (2025)

START: Self-taught Reasoner with Tools
by: Li, Chengpeng, et al.
Published: (2025)

PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
by: Zhang, Luan, et al.
Published: (2026)

Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning
by: Xu, Ningning, et al.
Published: (2025)

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
by: Qu, Changle, et al.
Published: (2026)