Dev Evolves FunSearch-Style Solutions for Bin Packing, MaxCut and Sorting Networks
cephaloform · x · 2026-11-14
A developer shares progress on a funsearch-style evolutionary search experiment: after RNN issues surfaced in the training environment, he split the project into optimizer engineering, curriculum ordering, and aux loss design submodules. The method has so far evolved working solutions on bin packing, maxcut, and sorting networks.
A follow-up notes that after 18 hours of running, no hits landed on problems beyond bin packing, and he plans to let it run a few more days before drawing conclusions.
More from Research
- Ai2's XYBench Finds Five Top LLMs Fail to Correct Users' Misguided Questions — allen_ai · 2026-11-14
- Ai2 Asks Whether Prompting or Training Can Make LLMs Give More Useful Advice — allen_ai · 2026-11-14
- Ai2's XYBench Wins EMNLP Best Resource Award, Exposing LLMs' XY Problem Blind Spot — allen_ai · 2026-11-14
- G-STAR paper: 32–64x token compression gives 20x faster autoregressive image generation — _akhaliq · 2026-11-14
- OpenCLIP 4.2 ships with CLAP2 variable-length audio and NaFlexViT support — wightmanr · 2026-11-14
- VIALS benchmark exposes weaknesses of vision encoders and tool-use agents — AllThingsApx · 2026-11-14