Autonomous systems that act — and what it takes to trust them.
Autonomous research agents can now generate, code and backtest their own trading factors. This paper asks the question that matters more than any single discovery — can you trust the process that found it?
arXiv:2609.00731
Ask a language model to import a package that doesn't exist or implement an algorithm that violates a proven theorem, and it will usually try anyway. A new benchmark measures exactly how often — and how rarely models refuse instead.
arXiv:2609.03267
SimSkill never touches its own weights. It gets better at traffic simulation purely by inventing its own practice tasks, verifying its own attempts, and filing what works into memory — a self-improvement loop with no fine-tuning in sight.
arXiv:2609.03753
Anthropic, Grab and Meta each shipped infrastructure work this week that, read together, sketches the early blueprint for running autonomous AI agents safely inside a real company.
3 papers
Today's AI coding agents close ten-minute tickets with ease. Give them a forty-hour project — port Kubernetes, clone Slack — and the best of them fail seven times out of ten.
arXiv:2606.07682
An AI agent follows a written rule most of the time — but "most of the time" is exactly where reliability dies. The craft is knowing which rules to prompt and which to enforce in code.
Anthropic