Finally! Congrats, a step in a great direction!
We've been stuck in this local optimum of "writing actions as JSON blobs with individual tool calls in them" for much too long. Just let models write tool calls in code blobs!
LLMS
-
Celebrating shift from JSON tool calls to code blobs
By
–
-
Retokenization and Language Knowledge in Model Training
By
–
The biggest question is whether you allow re-tokenization, and whether that should be done with the same data as the training itself. Right now there is knowledge about the language in existing tokens built-in and changing that is against the rules and/or unfavorable.
-

Rediscovery of CodeAct and smolagents a year later
By
–
I think they're finally going to rediscover CodeAct and smolagents, 1 year later!
-

ThinkMorph: Emergent Properties in Multimodal Chain-of-Thought
By
–
ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning Gu et al.: https://
arxiv.org/abs/2510.27492 #ArtificialIntelligence #DeepLearning #MachineLearning -

Google NotebookLM to add custom styles for video overviews
By
–
BREAKING : Google is working on Custom Styles for Overviews on NotebookLM. This option will let users set a custom prompt defining a visual style of the video. This also potentially means that Overviews will be powered by Nano Banana 2 very soon!
-
Building Efficient AI Agents with Model Context Protocol
By
–
New on the Anthropic Engineering blog: tips on how to build more efficient agents that handle more tools while using fewer tokens. Code execution with the Model Context Protocol (MCP):
-

Codex CLI Pull Requests Growth Compared to Gemini CLI
By
–
Counting PRs is a little silly, but there's a huge shift in the Codex CLI PRs since August – though still behind Gemini CLI PRs, which I did not expect. New Codex model would be pretty cool to have.
-

GradingBench releases 1000 human-graded IMO proof data points
By
–
Last but not least, #GradingBench has 1000 human grading data points from our IMO effort on the advanced IMO-ProofBench. To ensure a robust evaluation, the dataset has been balanced across 4 simplified grading categories (Correct, Almost, Partial, Incorrect). We released all
-
Gemini Deep Think achieves strong performance on FrontierMath benchmark
By
–
Hopefully, this thread is a good teaser to the strengths of Gemini Deep Think (IMO-gold) given that last month, Gemini Deep Think (IMO-lite) topped FrontierMath 😉
-

Grok 4 Overfitting Analysis ProofBench Advanced Leaderboard
By
–
For those of you who love leaderboards, here is one for the advanced #ProofBench 🙂 When breaking down performances into different subsets, we noticed potential overfitting in certain models and approaches. For example, Grok 4 (heavy) scores 76.2% on USAMO 2025 but only 11.1% on