AlphaEvolve paper: a coding agent for scientific and algorithmic discovery
RichardsonDx · x · 2026-11-12
DeepMind's AlphaEvolve paper (arXiv, June 2025) describes a coding agent for scientific and algorithmic discovery. It combines LLM-generated code with evolutionary search to iteratively improve algorithms and research artifacts, previously achieving state-of-the-art results on tasks like faster matrix multiplication and data center scheduling. Related follow-ups such as Meta's KernelEvolve show LLM-plus-evolutionary-search is becoming an active research direction for automated algorithm discovery.
More from coding & agent
- Dell expands AI Data Platform: agents have a data-context problem, not a model problem — DavidLinthicum · 2026-11-12
- Dev's favorite AI use case: Claude monitors competitors and emails alerts — doooyle · 2026-11-12
- LLM controls vocal synth to perform Ave Maria in 4-part harmony — AAAzzam · 2026-11-12
- ArcGrav: a cross-model Agent Control Language to cut token overhead — ArchitecturalGravity · 2026-11-12
- Claude watches competitors around the clock and emails me what matters — GlenBradley · 2026-11-12
- Developers say Gemini 4 Carbon is notably better at favicon design and micro-interactions — AI_Andrew · 2026-11-12