paper-with-me

Papers

Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs

2026-05-14 · Guangyu Feng, Huanzhi Mao, Prabal Dutta, Joseph E. Gonzalez arxiv

Function calling, also known as tool use, is a core capability of modern LLM agents but is typically constrained by synchronous execution semantics. Under these semantics, LLM decoding is blocked until each function call completes, resulting in increasing end-to-end latency. In this work, we introduce AsyncFC, a pure execution-layer framework that decouples LLM decoding from function execution, enabling overlap between model decoding and function execution as well as inter-function parallelism when dependencies permit. AsyncFC layers over existing models and unmodified function implementations, requiring no fine-tuning or changes to the standard synchronous function-calling protocol. Across standard function-calling benchmarks and adapted software engineering benchmarks, AsyncFC significantly reduces end-to-end task completion time while preserving task accuracy. Furthermore, these results reveal that LLMs possess a native capability to reason over symbolic futures that represent unresolved execution results, enabling an asynchronous paradigm for model-tool interaction.

📄 PDF Abstract BibTeX arXiv:2605.15077

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Inference Concurrency in DynamicGate MLP Structural and Mathematical Justification

2026-04-15 · Yongil Choi arxiv

Conventional neural networks strictly separate learning and inference because if parameters are updated during inference, outputs become unstable and even the inference function itself is not well defined [1, 2, 3]. This…

Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention

2026-03-01 · Mengqi Liao, Lu Wang, Chaoyun Zhang, Bo Qiao 외 arxiv

With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Althoug…

Mathematical Reasoning

Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis

2018-02-26 · Tal Ben-Nun, Torsten Hoefler

Deep Neural Networks (DNNs) are becoming an important tool in modern computing applications. Accelerating their training is a major challenge and techniques range from distributed algorithms to low-level circuit design. …

Deep LearningNeural Architecture SearchStochastic Optimization

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

2025-11-30 · Jiaming Tang, Yufei Sun, Yilong Zhao, Shang Yang 외 arxiv

Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, their real-world deployment remains slow and inefficient: demonstration videos are often sped up by 5-10x to a…

D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models

2026-05-13 · Yucheng Guo, Yongjian Guo, Zhong Guan, Wen Huang 외 arxiv

The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (RL) to these massive models in large-scal…

Reinforcement Learning