Researchers made AI agents better by turning academic papers into working code — no retraining required

ScholarEvolve uses published research to improve AI agents, raising Qwen's AppWorld task completion from 69% to 81.4% without retraining the model.
InfoQ

AWS Introduces Strands Decider 2B and Strands Box for AI Agent Development

AWS has introduced two open-source projects for AI agent development: Strands Decider 2B, a small model designed to make ...

Nobel Prize in Chemistry, Soai Reaction and the Frank Model: Let's take a peek at the mechanism where a 'slight bias' is amplified to 100% using Python! [Sna…

On October 7, 2026, the Royal Swedish Academy of Sciences announced that the 2026 Nobel Prize in Chemistry would be awarded ...

[AI Lab #1] Can running lots of cheap Claude Haiku 5.5 models beat Opus 5.5? After experimenting, it turns out there was no need to run them in large quantities at all

When using AI, little questions often pop up.If you ask an AI, it will return a plausible answer. But is that really true?In that case, let's actually try it out.I decided to start an "AI Lab" to ...
InfoQ

Android Bench 2 Adds Support for Long-Horizon Tasks, Agentic Evaluation, and Continuous Scoring

Google has released Android Bench 2.0, a major update to its benchmark framework for evaluating AI models and agents on Android development tasks. The update introduces long-horizon tasks (LHTs), ...
Ars Technica

Covert uploads and megalomania: OpenAI details new “misaligned” agent incidents

For a while now, the issue of “AI alignment” (i.e., how well an AI model’s actions line up with the intentions of its creator and/or user) has been a core concern and topic of discussion among AI ...