François Chollet et al. publish new benchmark ARC-AGI-3. As of March 2026, all Frontier LLMs have achieved less than 1% of the interactive task of autonomously exploring an unknown environment with an unknown goal.
AttnRes to replace Transformer's fixed residual combination with softmax attention in the depth direction. Demonstration with Kimi Linear 48B improved GPQA-Diamond +7.5pt and HumanEval +3.1pt. Training overhead was kept below 4% and inference below 2%.
Bartz v. Anthropic, a class action lawsuit over learning through unauthorized downloading from LibGen, etc., reaches settlement. FSF, as the copyright holder of the GNU FDL works, received the settlement notice and announced its position demanding disclosure of the training data model for LLM learning.
GitHub releases the layered defense design of the agent execution platform, and OpenAI releases the instruction hierarchy training data IH-Challenge and model. Responses to prompt injection were received from both infrastructure design and training axes.
HuggingFace conducts a comparative analysis of 16 open source RL training libraries based on 7 design axes. In the synchronous type, the GPU utilization remains at around 60% due to the generation bottleneck, but with an asynchronous separation design it can be improved to over 95%.
