In the news
NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry
arXiv cs.AI · Published · 3 min read
In 30 seconds
- llm
- language model
- reasoning
- benchmark
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.