Image de couverture de livre

HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liao, Weibin, Lou, Jian-guang, Xiong, Haoyi
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

MrBlankness/HyFunc: HyFunc -- KDD'26
par: Weibin Liao
Publié: (2026)

Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey
par: Guan, Shengyue, et autres
Publié: (2025)

GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling
par: Xu, Hao-Xiang, et autres
Publié: (2026)

HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
par: Xu, Beibei, et autres
Publié: (2026)

FuncGenFoil: Airfoil Generation and Editing Model in Function Space
par: Zhang, Jinouwen, et autres
Publié: (2025)

ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling
par: Zhang, Hanlong, et autres
Publié: (2025)

Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
par: Dang, Hy, et autres
Publié: (2025)

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
par: Zhao, Xiaochen, et autres
Publié: (2026)

Switchcraft: AI Model Router for Agentic Tool Calling
par: Agarwal, Sharad, et autres
Publié: (2026)

STRIDE: A Systematic Framework for Selecting AI Modalities -- Agentic AI, AI Assistants, or LLM Calls
par: Asthana, Shubhi, et autres
Publié: (2025)

FuncEvalGMN: Evaluating Functional Correctness of SQL via Graph Matching Network
par: Zhan, Yi, et autres
Publié: (2024)

Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis
par: Li, Junren, et autres
Publié: (2023)

HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study
par: Pitale, Mandar, et autres
Publié: (2025)

Asynchronous LLM Function Calling
par: Gim, In, et autres
Publié: (2024)

FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API
par: Kim, Juhyeong, et autres
Publié: (2025)

HyRRT-Connect: Bidirectional Motion Planning for Hybrid Dynamical Systems
par: Wang, Nan, et autres
Publié: (2025)

HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation
par: Tang, Weizhi, et autres
Publié: (2025)

HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data
par: Myung, Jiyoon, et autres
Publié: (2025)

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
par: Belkhiter, Yannis, et autres
Publié: (2026)

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
par: Cao, Bowen, et autres
Publié: (2026)

Towards Agentic AI on Particle Accelerators
par: Sulc, Antonin, et autres
Publié: (2024)

Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling
par: Bhan, Nirav, et autres
Publié: (2024)

Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents
par: Xiong, Haoyi, et autres
Publié: (2024)

Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set
par: Wu, Chengwei, et autres
Publié: (2025)

Performant LLM Agentic Framework for Conversational AI
par: Casella, Alex, et autres
Publié: (2025)

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
par: Wu, Qinyuan, et autres
Publié: (2026)

LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
par: Lin, Yu-Zheng, et autres
Publié: (2025)

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees
par: Liao, Weibin, et autres
Publié: (2024)

MimicFunc: Imitating Tool Manipulation from a Single Human Video via Functional Correspondence
par: Tang, Chao, et autres
Publié: (2025)

HyMoERec: Hybrid Mixture-of-Experts for Sequential Recommendation
par: Li, Kunrong, et autres
Publié: (2025)

ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
par: Li, Haoyun, et autres
Publié: (2026)

TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
par: Raza, Shaina, et autres
Publié: (2025)

HyReach: Vision-Guided Hybrid Manipulator Reaching in Unseen Cluttered Environments
par: Kamtikar, Shivani, et autres
Publié: (2026)

HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment
par: Yin, Zecheng, et autres
Publié: (2025)

Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
par: Ji, Zhenlan, et autres
Publié: (2025)

Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning
par: Jhandi, Polaris, et autres
Publié: (2025)

On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset
par: Bhat, Vishvesh, et autres
Publié: (2025)

Dynamic Agentic AI Expert Profiler System Architecture for Multidomain Intelligence Modeling
par: Adeseye, Aisvarya, et autres
Publié: (2026)

CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
par: Han, Yuning, et autres
Publié: (2026)

Position: Agentic AI System Is a Foreseeable Pathway to AGI
par: Liao, Junwei, et autres
Publié: (2026)