Clauday.

Let an agent write its own homework and grade it too, and eventually the proposer and the grader learn to make the same mistakes. "False Frontiers" (arXiv 2609.39102, 180 upvotes o…

The feared failure of chain-of-thought monitoring was secret code: a model under monitor pressure learning to hide its real reasoning in text humans cannot read. Julian Schulz's ne…

How little human is enough for an agent to build a frontier model? iCoder-27B is a serious attempt at a number. The humans did not run experiments. They wrote the rules: objectives…

Thinking models think too much. Fireworks says Kimi K3 spends sometimes more than 90% of its output tokens on internal reasoning, and in an agent loop that bill compounds, because …

LLMs can now prove theorems that stood open for decades. The next question is less glamorous and more important: out of everything a machine can prove, which theorems are worth hav…

Three million sandboxes created per day, per unit. 380,000 running at the same time. More than 5,000 new ones every second. Those are the production numbers in DeepSeek Elastic Com…

Can AI be both the thing being built and one of the builders? Qwen's answer, in Qwen-Planner-Agent (arXiv 2609.29892), is a closed loop where agents produce the data, shape the tra…

ReAct-style deep search agents ask one policy to do three jobs, plan the next query, read evidence, and write the answer, while dragging an ever-longer search history behind it. It…

Training a coding agent with reinforcement learning needs two things that are hard to get together: diverse tasks, and verifiers you can trust. CodeMidas, arXiv 2609.22068, submitt…

A paper from PhAI Labs, submitted September 16 and sitting near the top of Hugging Face daily papers, names a problem the agent field has been dancing around: the scientific experi…