AI Briefing#function-calling
The latest AI and developer news about #function-calling, with the original source and a short summary.
The latest AI and developer news about #function-calling, with the original source and a short summary.
Liquid AI released a 3.1B vision-language model with enhanced screen understanding and tool use.
Meta has open-sourced Muse Glimmer, a 30-billion-parameter model for local agents.
As LLMs can incorrectly call functions and cause serious risks, uncertainty quantification techniques that measure the accuracy of calls are becoming important.
This case study covers how GloZ uses Amazon OpenSearch and Claude Haiku to transform natural language queries into search DSL and optimize hybrid search.
Needle, an ultra-lightweight AI model with just 26M parameters distilled from Gemini 3.1, has been released.
Needle has open-sourced a Gemini-based tool-calling model with 26 million parameters.
The function calling harness has narrowed the frontier-local gap in backend generation.
AutoBe has released a monthly benchmark comparing backend generation by GLM, Qwen, and DeepSeek.
It explains that schema validation raised the CoT compliance rate from 9.91% to 100%.
Claude Code lazily loads tool schemas via ToolSearch instead of sending them all at once.
Google has released LiteRT-LM, its on-device LLM inference engine.
It compiles English function descriptions into 22MB neural programs that run locally on llama.cpp.
Google Gemma 4 26B MoE and 31B Dense are now available on Vercel AI Gateway.
Using AutoBe and Typia, a deterministic feedback loop overcomes low Function Calling success rates and pushes them close to 100%.
Function Calling, RAG, and LangGraph were used to improve the accuracy and operability of a consultation-style chatbot.
KakaoPay adopted **MCP** to efficiently connect AI agents with its payment API, and developed a multi-framework **Agent Toolkit**.
Retell AI unveiled a voice agent automation solution powered by GPT-4o that enables natural conversations without any coding.
Kakao has released Kanana 1.5 8B and 2.1B models under the Apache 2.0 license, allowing for commercial use.
Mistral AI has unveiled new models optimized for on-device and edge computing, Ministral 3B and 8B.
Hugging Face has released a unified Tool Use API that is compatible across various model families.
OpenAI has introduced a Structured Outputs feature to the API that ensures model outputs perfectly comply with developer-provided JSON schemas.
NPC-Playground, an open-source project that implements intelligent NPCs in 3D environments using LLMs' function calling capabilities, has been unveiled.