Weekly Reads

Recursive Multi-Agent Systems — Xiyuan Yang, Jiaru Zou et al.
Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent stat...
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios — Jinxiang Meng, Shaoping Huang et al.
Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing...
How Fast Should a Model Commit to Supervision? Training Reasoning Models on the Tsallis Loss Continuum — Chu-Cheng Lin, Eugene Ie
Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable ...
A paradox of AI fluency — Christopher Potts, Moritz Sudhof
How much does a user's skill with AI shape what AI actually delivers for them? This question is critical for users, AI product builders, and societ...
Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics — Andre Herz, Daniel Durstewitz, Georgia Koppe
Identity teacher forcing (ITF) enables stable training of deterministic recurrent surrogates for chaotic dynamical systems and has been highly effe...

AI evals are becoming the new compute bottleneck — Hugging Face Blog
Granite 4.1 LLMs: How They’re Built — Hugging Face Blog
Building the compute infrastructure for the Intelligence Age — OpenAI Blog
OpenAI scales Stargate to build the compute infrastructure powering AGI, adding new data center capacity to meet growing AI demand.