Copertina

Dynamic Tool Dependency Retrieval for Lightweight Function Calling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Patel, Bhrij, Belli, Davide, Jalalirad, Amir, Arnold, Maximilian, Ermolov, Aleksandr, Major, Bence
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Neural Augmented Kalman Filters for Road Network assisted GNSS positioning
di: van Gorp, Hans, et al.
Pubblicazione: (2025)

GNSS Positioning using Cost Function Regulated Multilateration and Graph Neural Networks
di: Jalalirad, Amir, et al.
Pubblicazione: (2024)

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking
di: Federici, Marco, et al.
Pubblicazione: (2024)

Neural 5G Indoor Localization with IMU Supervision
di: Ermolov, Aleksandr, et al.
Pubblicazione: (2024)

Vision-Assisted Digital Twin Creation for mmWave Beam Management
di: Arnold, Maximilian, et al.
Pubblicazione: (2024)

Multi-LLM QA with Embodied Exploration
di: Patel, Bhrij, et al.
Pubblicazione: (2024)

When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
di: Rainone, Corrado, et al.
Pubblicazione: (2026)

Code Comprehension then Auditing for Unsupervised LLM Evaluation
di: Patel, Bhrij, et al.
Pubblicazione: (2024)

Learning API Functionality from In-Context Demonstrations for Tool-based Agents
di: Patel, Bhrij, et al.
Pubblicazione: (2025)

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

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

TinyAgent: Function Calling at the Edge
di: Erdogan, Lutfi Eren, et al.
Pubblicazione: (2024)

Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
di: Patel, Bhrij, et al.
Pubblicazione: (2024)

Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
di: Hooper, Coleman, et al.
Pubblicazione: (2026)

ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
di: Ding, Peng, et al.
Pubblicazione: (2025)

Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling
di: Ding, Peng, et al.
Pubblicazione: (2025)

Stateful Inference for Low-Latency Multi-Agent Tool Calling
di: Norgren, Victor
Pubblicazione: (2026)

SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety
di: Xu, Zixuan, et al.
Pubblicazione: (2026)

Agentic Retrieval of Topics and Insights from Earnings Calls
di: Gupta, Anant, et al.
Pubblicazione: (2025)

LightFF: Lightweight Inference for Forward-Forward Algorithm
di: Aminifar, Amin, et al.
Pubblicazione: (2024)

Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
di: Patel, Bhrij, et al.
Pubblicazione: (2023)

Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models
di: Balasubramanian, Krishnakumar, et al.
Pubblicazione: (2026)

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

Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL
di: de Costa, Mishca, et al.
Pubblicazione: (2025)

Better Call Graphs: A New Dataset of Function Call Graphs for Malware Classification
di: Hossain, Jakir, et al.
Pubblicazione: (2025)

Functional Latent Dynamics for Irregularly Sampled Time Series Forecasting
di: Klötergens, Christian, et al.
Pubblicazione: (2024)

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
di: Knorr, Marius S., et al.
Pubblicazione: (2026)

LyZNet: A Lightweight Python Tool for Learning and Verifying Neural Lyapunov Functions and Regions of Attraction
di: Liu, Jun, et al.
Pubblicazione: (2024)

Reinforced Agent: Inference-Time Feedback for Tool-Calling Agents
di: Ta, Anh, et al.
Pubblicazione: (2026)

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

Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
di: Feoktistov, Dmitrii, et al.
Pubblicazione: (2026)

Learning in Markov Decision Processes with Exogenous Dynamics
di: Maran, Davide, et al.
Pubblicazione: (2026)

Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks
di: Abdelaziz, Ibrahim, et al.
Pubblicazione: (2024)

A Retrieval-Enhanced Transformer for Multi-Step Port-of-Call Sequence Prediction in Global Liner Shipping
di: Su, Yanzhao, et al.
Pubblicazione: (2026)

RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs
di: Tan, Bowen, et al.
Pubblicazione: (2023)

Tool Calling is Linearly Readable and Steerable in Language Models
di: Wu, Zekun, et al.
Pubblicazione: (2026)

DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes
di: Bolgár, Bence, et al.
Pubblicazione: (2025)

Characterization of Transfer Using Multi-task Learning Curves
di: Millinghoffer, András, 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)

Re:Frame -- Retrieving Experience From Associative Memory
di: Zelezetsky, Daniil, et al.
Pubblicazione: (2025)