Imagen de Portada

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Qinyuan, Das, Soumi, Amani, Mahsa, Nag, Arijit, Lee, Seungeon, Gummadi, Krishna P., Ravichander, Abhilasha, Zafar, Muhammad Bilal
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations
por: Khan, Mohammad Aflah, et al.
Publicado: (2026)

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging
por: Lee, Seungeon, et al.
Publicado: (2025)

Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
por: Wu, Qinyuan, et al.
Publicado: (2025)

Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models
por: Das, Soumi, et al.
Publicado: (2025)

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
por: Shi, Wei, et al.
Publicado: (2026)

GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
por: Ahn, Kyeongjin, et al.
Publicado: (2026)

Characterizing Web Search in The Age of Generative AI
por: Kirsten, Elisabeth, et al.
Publicado: (2025)

Asynchronous LLM Function Calling
por: Gim, In, et al.
Publicado: (2024)

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

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

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

Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE
por: Khan, Mohammad Aflah, et al.
Publicado: (2026)

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

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents
por: Chinaei, Mohammad Hossein
Publicado: (2026)

Interleaved Tool-Call Reasoning for Protein Function Understanding
por: Fan, Chuanliu, et al.
Publicado: (2026)

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

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

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

The Algorithmic Self-Portrait: Deconstructing Memory in ChatGPT
por: Dash, Abhisek, et al.
Publicado: (2026)

Switchcraft: AI Model Router for Agentic Tool Calling
por: Agarwal, Sharad, et al.
Publicado: (2026)

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
por: Ravichander, Abhilasha, et al.
Publicado: (2025)

When2Call: When (not) to Call Tools
por: Ross, Hayley, et al.
Publicado: (2025)

Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
por: Li, Henger, et al.
Publicado: (2025)

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
por: Ma, SHengjie, et al.
Publicado: (2025)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
por: Zhu, Jinhao, et al.
Publicado: (2025)

IM-Chat: A Multi-agent LLM Framework Integrating Tool-Calling and Diffusion Modeling for Knowledge Transfer in Injection Molding Industry
por: Lee, Junhyeong, et al.
Publicado: (2025)

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

Optimizing Agentic Language Model Inference via Speculative Tool Calls
por: Nichols, Daniel, et al.
Publicado: (2025)

What Has Been Lost with Synthetic Evaluation?
por: Gill, Alexander, et al.
Publicado: (2025)

Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
por: Ji, Zhenlan, et al.
Publicado: (2025)

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

ASA: Training-Free Representation Engineering for Tool-Calling Agents
por: Wang, Youjin, et al.
Publicado: (2026)

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

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

AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agents
por: Kurmaz, Mehmet
Publicado: (2026)

Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
por: Cartagena, Arnold, et al.
Publicado: (2026)

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

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

CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices
por: Paramanayakam, Varatheepan, et al.
Publicado: (2025)

Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents
por: Zhou, Kaiyu, et al.
Publicado: (2026)