AI Briefing#tool-calling
The latest AI and developer news about #tool-calling, with the original source and a short summary.
The latest AI and developer news about #tool-calling, with the original source and a short summary.
Tether AI released BotPsy-0.8B, based on Qwen3.5-0.8B, demonstrating superior tool-use performance compared to 2B models.
The tools work with any model supporting tool calling via a single AI Gateway API key, requiring no separate DeepSeek account.
The system separates LLM interpretation from code-based calculation to ensure accurate daily reports for LINE OA and Display Ads.
Enabling the vLLM 0.31 server-side constrained decoding flag improved tool-call schema accuracy from 92% to 100% for Kimi K2.6 and DeepSeek models.
The 10B-parameter model uses roughly 2-4x fewer reasoning tokens than leading peers while maintaining comparable accuracy.
A type-aware chat template patch resolved rendering failures in Qwen-based coding agents without degrading model performance, highlighting that tool loops often stem from serialization errors rather than model behavior.
The tools are available in AI SDK 7.0.116 and later, allowing models to access current web information via a single API key.
The new MOPD-based solution reduced repetition rates significantly at a cost of approximately $90,000, compared to an estimated $2.31 million for a full MixRL restart.
Cactus Compute has released 'Needle 3', an ultra-compact foundation model ranging from 29MB to 121MB, stating that its 4-layer subnetwork achieves automation performance equivalent to DeepSeek V4 Flash.
This article analyzes the Tool Calling loop structure and cost issues arising from the Stateless nature of AI Agents implemented in Vanilla JS, introducing cost optimization methods through Prefix caching and four essential implementation rules.
Tool Calling is a core feature that enables LLMs to connect with external APIs and data in real time, reducing hallucinations and automating complex tasks.
Apple released PROOF-Gen, which recovers failed tool-calling scenarios to significantly improve model distillation performance.
The llama.cpp server now supports executing tools within sandbox containers using Podman or Docker.
Cactus has released Needle 2, a 14MB on-device agentic LLM.
NVIDIA released an 11B voice model supporting 450ms response times and tool calling.
llama.cpp has fixed a tool calling issue in DeepSeek v4 Flash 0731.
Google has updated Gemma 4's chat template to improve tool calling performance and now supports Flash Attention 4.
Sponsio, an open-source project that deterministically controls tool-call boundaries for LLM agents, has been released.
The llama.cpp server now supports native tool-calling capabilities, including file manipulation and shell command execution.
Forge is an open-source guardrail layer that improves the tool-calling stability of local LLMs.
Forge, a guardrail framework that improves tool-calling reliability of local LLMs, has been released.
Needle, a distillation of Gemini tool calling into a 26-million-parameter model, has been released.
Introduced a way to run the LLM CLI like a script by putting it in the shebang line.