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.
Google has made Gemini 3.1 Flash-Lite generally available.
In CC 2.1.128, background agent instructions and the model catalog have changed.
Adding inference-time review to tool-calling agents reduced errors before execution.
MCP servers should guide the next call themselves, rather than relying on the model to plan it.
The command-line LLM tool `llm` has been updated to 0.32a1, fixing a SQLite conversation restoration bug.
Thoth v3.18 adds MCP integration, secure key storage, and migration features.
Version 0.32a0 of the command-line LLM tool llm has been released.
IBM has unveiled Granite-4.1-30B, a 30B-scale model with enhanced tool calling and multilingual capabilities.
A bug in Gemma 4's chat template that failed to handle complex JSON Schema has been fixed.
It was confirmed that the DeepSeek V4 API has a technical requirement to always pass back reasoning_content when Tool Calls are involved.
A parser error in vLLM was found to cause malfunctioning Tool Calling functionality in Qwen models.
Outlines the structure for attaching local AI to Manifest V3 Chrome extensions using Transformers.js.
Kimi Vendor Verifier validates implementation deviations across inference providers.
IBM has released Granite-4.1-8B, enhancing tool calling and instruction-following performance.
Qwen 3.6 35B-A3B has been quantized for Ollama, supporting even tools and thinking.
Uniform quantization breaks Qwen3.5's sensitive layers.
On M3 Ultra, Qwen 3.6 35B achieved a 100% tool-calling success rate across most of the 5 agent frameworks.
On refined data, 1.7B beat 744B, but noisy traces collapsed performance.
Qwen3-1.7B surpassed GLM-5 744B using only synthetic data fine-tuning.
In Gemma 4 26B a4b, multi-step think/tool loops break off midway.
Gemma 4 was connected to the local Codex CLI to verify its tool-calling performance and stability.
ElevenLabs has integrated Gemini 2.5 Flash into its Conversational AI platform, strengthening voice agent capabilities for enterprises.
Gemma 4's tool calling and dialog compliance have improved, requiring a Jinja template update.