Image de couverture de livre

Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sadani, Anuj, Kumar, Deepak
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models
par: Sadani, Anuj, et autres
Publié: (2026)

Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
par: Zhang, Kaituo, et autres
Publié: (2026)

ToolRL: Reward is All Tool Learning Needs
par: Qian, Cheng, et autres
Publié: (2025)

Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
par: Gaurav, Nishant, et autres
Publié: (2025)

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
par: Li, Ruiqi, et autres
Publié: (2026)

GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation
par: Zhou, Yitong, et autres
Publié: (2026)

TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
par: Sakizli, Furkan
Publié: (2026)

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
par: Le, Quy Minh, et autres
Publié: (2025)

MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
par: Wang, Wenhao, et autres
Publié: (2025)

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets
par: Sakizli, Furkan
Publié: (2026)

Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
par: Mudunuri, Sarat, et autres
Publié: (2026)

ToolRM: Towards Agentic Tool-Use Reward Modeling
par: Li, Renhao, et autres
Publié: (2025)

ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
par: Deng, Mengjie, et autres
Publié: (2025)

Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows
par: Mohammadi, Bardia, et autres
Publié: (2026)

Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs
par: Franko, Uria
Publié: (2025)

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
par: Mo, Guozhao, et autres
Publié: (2025)

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
par: Fei, Xiang, et autres
Publié: (2025)

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
par: Li, Yuanyang, et autres
Publié: (2026)

MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers
par: Bandi, Chaithanya, et autres
Publié: (2026)

Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance
par: Sigdel, Akshey, et autres
Publié: (2026)

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
par: Xu, Zhangchen, et autres
Publié: (2025)

Transduction is All You Need for Structured Data Workflows
par: Gliozzo, Alfio, et autres
Publié: (2025)

Attention is All You Need Until You Need Retention
par: Yaslioglu, M. Murat
Publié: (2025)

Control Plane as a Tool: A Scalable Design Pattern for Agentic AI Systems
par: Kandasamy, Sivasathivel
Publié: (2025)

Tools as Continuous Flow for Evolving Agentic Reasoning
par: Huang, Tairan, et autres
Publié: (2026)

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
par: Liu, Yanming, et autres
Publié: (2026)

PyVision: Agentic Vision with Dynamic Tooling
par: Zhao, Shitian, et autres
Publié: (2025)

Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows
par: Strickland, Joel, et autres
Publié: (2026)

Quantitative Certification of Agentic Tool Selection
par: Yeon, Jehyeok, et autres
Publié: (2025)

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
par: Guo, Zikang, et autres
Publié: (2025)

ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems
par: Sigdel, Akshey, et autres
Publié: (2026)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
par: Wang, Che, et autres
Publié: (2026)

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web
par: Yao, Zhiyuan, et autres
Publié: (2026)

ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use
par: Liu, Shusen, et autres
Publié: (2025)

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning
par: Yue, Murong, et autres
Publié: (2025)

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
par: Wang, Jize, et autres
Publié: (2026)

Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
par: Jamshidi, Saeid, et autres
Publié: (2026)

From Tool Orchestration to Code Execution: A Study of MCP Design Choices
par: Felendler, Yuval, et autres
Publié: (2026)

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
par: Jiang, Dongfu, et autres
Publié: (2025)

Element-wise Attention Is All You Need
par: Feng, Guoxin
Publié: (2025)