1
Show HN: AIfunc – Call AI as a function, not as an agent
把AI当函数调用，轻松搞定80%的日常AI需求，告别复杂Agent
Article URL: https://github.com/aifunc-dev/aifunc/ Comments URL: https://news.ycombinator.com/item?id=48831383 Points: 1 # Comments: 0
2
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
最新研究发现，通过模拟审核轨迹可绕过函数调用LLM的安全限制，揭示大模型越狱攻击新路径。
arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). W…
3
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
紧凑模型代理也能玩转复杂工具链？这篇论文提出推理时进化工作流，让小型语言模型自主发现、编排和执行MCP工具，实现成本与性能双赢。
arXiv:2606.12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents. Yet MCP-style…
4
R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling
提出R2IF框架，用复合奖励让大模型函数调用时推理与决策对齐，提升可解释性。
arXiv:2604.20316v2 Announce Type: replace Abstract: Function calling empowers large language models (LLMs) to interface with external tools, yet exist…
5
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
专为大模型函数调用设计的协议无关工具管理库，高效整合多源工具。
arXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a seriali…
6
Reflective Prompt Tuning through Language Model Function-Calling
通过函数调用实现反思性提示调优，让大模型动态优化自身提示，提升对话质量与适应性。
arXiv:2605.21781v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly capable of following instructions and complex re…
7
Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
无需微调模型，无需修改函数协议，AsyncFC 在纯执行层实现异步并发，让 LLM 解码与函数执行重叠，大幅降低端到端延迟。LLM 对未执行结果（symbolic futures）的推理能力被天然利用，开启模型-工具异步交互新范式。
arXiv:2605.15077v1 Announce Type: cross Abstract: Function calling, also known as tool use, is a core capability of modern LLM agents but is typically…