Google has released Gemini 3.8 Live and 3.8 Live Extended Thinking with asynchronous tool execution capabilities.

// 3h agoMODEL RELEASE

Google has released Gemini 3.8 Live and 3.8 Live Extended Thinking with asynchronous tool execution capabilities.

Google has launched Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, bringing asynchronous tool execution and advanced background reasoning to real-time, low-latency conversational models. These models allow complex, multi-step background tasks to be processed while simultaneously maintaining a continuous live audio stream with the user.

// ANALYSIS

The ability to execute tools asynchronously while holding a live conversation is a major leap forward for agentic voice assistants.

–This solves the latency and "awkward silence" problems when a voice agent needs to fetch data or execute a slow API call.
–Extended Thinking enables the model to perform highly complex reasoning tasks seamlessly in the background.
–Opens up robust enterprise possibilities for real-time customer support, inventory management, and interactive troubleshooting.

// TAGS

googlegeminiaillmvoice-agentsautonomous-agents

DISCOVERED

3h ago

2026-09-19

PUBLISHED

17h ago

2026-09-18

RELEVANCE

10/ 10

AUTHOR

octavusai

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH43m ago

ScientistTwo automates end-to-end scientific research

Developed by Google Cloud AI Research and the University of Waterloo, ScientistTwo is an autonomous multi-agent system designed to handle the complete scientific research lifecycle at scale. Spanning ten AI domains, the framework autonomously generates hypotheses, executes code in sandboxes, runs automated ablation studies, drafts academic manuscripts, and performs simulated peer-review cycles where rebuttal agents run new empirical experiments to address critiques.

OPEN SOURCE1h ago

Classifier.dev launches semantic-ci-lint for PR reviews

semantic-ci-lint is an open-source skill and CI workflow from classifier.dev that checks changed git diff hunks against codebase conventions written in prose, such as error-handling guidelines and PII logging restrictions. Instead of passing whole source files into generative LLMs, the tool uses a lightweight Python script with git diff -U0 to evaluate added lines against single-convention prompts via classifier.dev's keyless zero-shot classification API.

OPEN SOURCE2h ago

MiniMax open-sources MiniMax Code coding agent

MiniMax has announced the open-source release of MiniMax Code, bringing its agentic software engineering capabilities into developers' local environments via a terminal CLI and desktop workspace. By opening up the project, MiniMax aims to give developers full visibility into the tradeoffs of autonomous coding agents, enabling teams to execute commands locally, coordinate multi-agent tasks, and customize agent behaviors to fit their own development toolchains.

Google has released Gemini 3.8 Live and 3.8 Live Extended Thinking with asynchronous tool execution capabilities.