Copertina

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zeng, Yirong, Ding, Xiao, Wang, Yuxian, Liu, Weiwen, Ning, Wu, Hou, Yutai, Huang, Xu, Tang, Duyu, Tu, Dandan, Qin, Bing, Liu, Ting
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
di: Zeng, Yirong, et al.
Pubblicazione: (2025)

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
di: Zeng, Yirong, et al.
Pubblicazione: (2026)

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
di: Zeng, Yirong, et al.
Pubblicazione: (2026)

Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following
di: Zeng, Yirong, et al.
Pubblicazione: (2026)

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
di: Huang, Xu, et al.
Pubblicazione: (2025)

ToolACE: Winning the Points of LLM Function Calling
di: Liu, Weiwen, et al.
Pubblicazione: (2024)

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
di: Xu, Haoyuan, et al.
Pubblicazione: (2026)

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
di: He, Yang, et al.
Pubblicazione: (2026)

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning
di: Ye, Yangfan, et al.
Pubblicazione: (2025)

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

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios
di: Huang, Shijue, et al.
Pubblicazione: (2024)

Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuning
di: Huo, Wenshuai, et al.
Pubblicazione: (2025)

Concise and Precise Context Compression for Tool-Using Language Models
di: Xu, Yang, et al.
Pubblicazione: (2024)

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
di: Feng, Jiazhan, et al.
Pubblicazione: (2025)

Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents
di: Tan, Weiting, et al.
Pubblicazione: (2025)

LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning
di: Ye, Yangfan, et al.
Pubblicazione: (2025)

Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use
di: Zhang, Yabo, et al.
Pubblicazione: (2025)

Advancing SLM Tool-Use Capability using Reinforcement Learning
di: Paprunia, Dhruvi, et al.
Pubblicazione: (2025)

Learning Fine-Grained Grounded Citations for Attributed Large Language Models
di: Huang, Lei, et al.
Pubblicazione: (2024)

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
di: Wang, Zezhong, et al.
Pubblicazione: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
di: Guo, Jiahe, et al.
Pubblicazione: (2026)

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
di: Xu, Siyuan, et al.
Pubblicazione: (2026)

Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
di: Li, Wenjun, et al.
Pubblicazione: (2025)

Fine-Tuning is Fine, if Calibrated
di: Mai, Zheda, et al.
Pubblicazione: (2024)

ToolRM: Towards Agentic Tool-Use Reward Modeling
di: Li, Renhao, et al.
Pubblicazione: (2025)

Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns
di: Zhao, Yang, et al.
Pubblicazione: (2024)

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

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning
di: Zeng, Xingshan, et al.
Pubblicazione: (2025)

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
di: Zhang, Kangning, et al.
Pubblicazione: (2025)

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
di: Yang, Zuhao, et al.
Pubblicazione: (2026)

CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
di: Chen, Jinpeng, et al.
Pubblicazione: (2026)

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
di: Jiang, Dongfu, et al.
Pubblicazione: (2025)

Tool-integrated Reinforcement Learning for Repo Deep Search
di: Ma, Zexiong, et al.
Pubblicazione: (2025)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
di: Zhang, Kexun, et al.
Pubblicazione: (2023)

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict
di: Zeng, Yirong, et al.
Pubblicazione: (2024)

Ensuring Consistency for In-Image Translation
di: Fu, Chengpeng, et al.
Pubblicazione: (2024)

SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration
di: Shen, Yuanhao, et al.
Pubblicazione: (2024)

PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use
di: Wang, Qihao, et al.
Pubblicazione: (2026)

ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
di: Zeng, Xingshan, et al.
Pubblicazione: (2025)

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
di: Xiong, Kai, et al.
Pubblicazione: (2024)