arXiv AI
Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
arXiv:2605.27995v3 Announce Type: replace Abstract: Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluation...
arXiv AI
Oct 7
SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding
arXiv:2610.07086v1 Announce Type: cross Abstract: LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool sc...
arXiv AI
Jul 28
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
arXiv:2607. 23933v1 Announce Type: cross Abstract: As LLM agents increasingly rely on the Model Context Protocol (MCP) to invoke isolated external sandboxes, disaggregated sandbox deployment introduces a fundamental tension between resource utilization and interactive tail latency.
arXiv AI
Aug 25
Small Reasoning Models are Instruction Followers in Function Calling
arXiv:2608.22472v1 Announce Type: new Abstract: Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calli...
arXiv AI
Jun 9
RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models
arXiv:2606. 08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation.
arXiv AI
Sep 18
PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces
PetriBench is a compact, fully self‑contained, and scalable benchmark that evaluates large language model (LLM) reasoning over dynamic state spaces using Petri nets. It organizes reasoning into four task families with Easy, Medium, and Hard levels, each generated by increasing structural complexity and evaluated against exact ground truth. Experiments across proprietary and open‑weight models show that accuracy consistently drops with difficulty, revealing distinct task‑specific capability profiles, while test‑time compute and procedural generation affect performance differently across tasks.