Copertina

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Kangning, Jiao, Wenxiang, Du, Kounianhua, Lu, Yuan, Liu, Weiwen, Zhang, Weinan, Yu, Yong
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

Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering
di: Du, Kounianhua, et al.
Pubblicazione: (2025)

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

From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop
di: de la Torre, Jordi
Pubblicazione: (2025)

Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets
di: Gao, Xin, et al.
Pubblicazione: (2025)

MeNTi: Bridging Medical Calculator and LLM Agent with Nested Tool Calling
di: Zhu, Yakun, et al.
Pubblicazione: (2024)

MMSkills: Towards Multimodal Skills for General Visual Agents
di: Zhang, Kangning, et al.
Pubblicazione: (2026)

SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback
di: Yu, Yaoning, et al.
Pubblicazione: (2025)

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

Way to Specialist: Closing Loop Between Specialized LLM and Evolving Domain Knowledge Graph
di: Zhang, Yutong, et al.
Pubblicazione: (2024)

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

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

An LLM-Tool Compiler for Fused Parallel Function Calling
di: Singh, Simranjit, et al.
Pubblicazione: (2024)

CodeApex: A Bilingual Programming Evaluation Benchmark for Large Language Models
di: Fu, Lingyue, et al.
Pubblicazione: (2023)

Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
di: Tang, Zinan, et al.
Pubblicazione: (2025)

ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues
di: Khandelwal, Dinesh, et al.
Pubblicazione: (2026)

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
di: Wang, Jingxing, et al.
Pubblicazione: (2026)

DiLA: Enhancing LLM Tool Learning with Differential Logic Layer
di: Zhang, Yu, et al.
Pubblicazione: (2024)

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning
di: Yue, Murong, et al.
Pubblicazione: (2025)

Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM
di: Haque, Mohd Ariful, et al.
Pubblicazione: (2025)

Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
di: Luo, Zheng, et al.
Pubblicazione: (2026)

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

Benchmarking LLM Tool-Use in the Wild
di: Yu, Peijie, et al.
Pubblicazione: (2026)

Ghost Tool Calls: Issue-Time Privacy for Speculative Agent Tools
di: Mohammadi, Bardia, et al.
Pubblicazione: (2026)

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

Tool-Planner: Task Planning with Clusters across Multiple Tools
di: Liu, Yanming, et al.
Pubblicazione: (2024)

Latent Preference Modeling for Cross-Session Personalized Tool Calling
di: Yoon, Yejin, et al.
Pubblicazione: (2026)

SoK: Measuring What Matters for Closed-Loop Security Agents
di: Khurana, Mudita, et al.
Pubblicazione: (2025)

Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
di: Zhu, Jiachen, et al.
Pubblicazione: (2025)

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
di: Xi, Yunjia, et al.
Pubblicazione: (2025)

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use
di: Zeng, Yirong, et al.
Pubblicazione: (2025)

CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models
di: Wu, Yuning, et al.
Pubblicazione: (2026)

Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
di: Wong, Jeffrey T. H., et al.
Pubblicazione: (2026)

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
di: Chai, Huacan, et al.
Pubblicazione: (2025)

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback
di: Wu, Qinzhuo, et al.
Pubblicazione: (2024)

Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection
di: Zhang, Fanrui, et al.
Pubblicazione: (2025)

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
di: Zhang, Shaokun, et al.
Pubblicazione: (2025)

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

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
di: Lu, Jiarui, et al.
Pubblicazione: (2024)

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
di: Ye, Junjie, et al.
Pubblicazione: (2024)

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
di: Zhao, Yufeng, et al.
Pubblicazione: (2025)