RADAR / WEEKLY
This week in AI: source excerpts and reading links, grouped by original publication week.
TOP SIGNALS
WHAT CHANGED / SOURCE SIGNALS
RADAR / SIGNAL · AGENTS · PAPER ·
SOURCE EXCERPT
Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelines. Yet existing evaluations…
RADAR / SIGNAL · AGENTS · PAPER ·
SOURCE EXCERPT
Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evalu…
WHAT CHANGED / SOURCE SIGNALS
RADAR / SIGNAL · EMBODIED-AI · PAPER ·
SOURCE EXCERPT
Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-robot embodiment gap, existi…
RADAR / SIGNAL · EMBODIED-AI · PAPER ·
SOURCE EXCERPT
Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policies trained purely from dem…
WORTH FOLLOWING