Imagen de Portada

The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Haoyuan, Li, Chang, Ma, Xinyan, Ou, Xianhao, Zhang, Zihan, He, Tao, Liu, Xiangyu, Wang, Zixiang, Liang, Jiafeng, Chu, Zheng, Liu, Runxuan, Mu, Rongchuan, Tu, Dandan, Liu, Ming, Qin, Bing
Formato:	Preprint
Publicado:	2026
Materias:	Software Engineering Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification
por: Ma, Xinyan, et al.
Publicado: (2026)

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

Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models
por: Liu, Runxuan, et al.
Publicado: (2026)

Utility-Guided Agent Orchestration for Efficient LLM Tool Use
por: Liu, Boyan, et al.
Publicado: (2026)

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

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

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

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

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

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
por: Liang, Yijuan, et al.
Publicado: (2026)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
por: Hu, Xuhao, et al.
Publicado: (2026)

Imprompter: Tricking LLM Agents into Improper Tool Use
por: Fu, Xiaohan, et al.
Publicado: (2024)

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

OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
por: Chen, Jianming, et al.
Publicado: (2026)

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

ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
por: Liu, Marianne Menglin, et al.
Publicado: (2025)

TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling
por: Doh, Seungheon, et al.
Publicado: (2025)

LLM2Fx-Tools: Tool Calling For Music Post-Production
por: Doh, Seungheon, et al.
Publicado: (2025)

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

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

Enhancing Tool Calling in LLMs with the International Tool Calling Dataset
por: Zhang, Zuoyu, et al.
Publicado: (2026)

MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
por: Liu, Wenrui, et al.
Publicado: (2025)

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
por: Wang, Haowei, et al.
Publicado: (2024)

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
por: Su, Hongjin, et al.
Publicado: (2025)

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
por: Wu, Qinyuan, et al.
Publicado: (2026)

SimpleTool: Parallel Decoding for Real-Time LLM Function Calling
por: Shi, Xiaoxin, et al.
Publicado: (2026)

Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use
por: Pahwa, Ramit, et al.
Publicado: (2026)

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
por: He, Tao, et al.
Publicado: (2025)

Online-Optimized RAG for Tool Use and Function Calling
por: Pan, Yu, et al.
Publicado: (2025)

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

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
por: Chen, Xuan, et al.
Publicado: (2026)

Semantic Context for Tool Orchestration
por: Müller, Robert
Publicado: (2025)

ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs
por: Kokane, Shirley, et al.
Publicado: (2024)

Alignment for Efficient Tool Calling of Large Language Models
por: Xu, Hongshen, et al.
Publicado: (2025)

LLM Agents Already Know When to Call Tools -- Even Without Reasoning
por: Sun, Chung-En, et al.
Publicado: (2026)

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

ToolGen: Unified Tool Retrieval and Calling via Generation
por: Wang, Renxi, et al.
Publicado: (2024)

Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
por: Guo, Ruocheng, et al.
Publicado: (2026)

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

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