LLM-guided evolutionary search for algorithms: keeping 'weaker' candidates lifts solution quality 0.81→0.99
bravo_abad · x · 2026-10-05
Gong et al. use LLM-guided evolutionary search to design algorithms for routing, scheduling and resource-allocation problems. Candidates survive selection based on what they add to the existing set — a lower-scoring algorithm can cover weaknesses others miss. Expanding from one algorithm to ten raised solution quality from 0.81 to 0.99 (1 = best-known reference), running candidates on separate CPU cores and keeping the best valid answer, at the cost of more compute.
More from Research
- Study: DeepSeek's mHC Uses Only Two of Four Residual Streams, Deep Mixing Goes Near-Identity — jiqizhixin · 2026-10-05
- Frank Nielsen's free textbook: An Elementary Introduction to Information Geometry — FrnkNlsn · 2026-10-05
- Microsoft's ThinkingBox: grade agents by database changes, not their words — SergioPaniego · 2026-10-05
- Quanta: Is AI the End of Math As We Know It? — littmath · 2026-10-05
- First-of-Kind RCT: GPT-4o Respiratory Chatbot Beats Web Search for Layperson Diagnosis — EricTopol · 2026-10-05
- Local sparsity enables unsupervised LLM safety detection, new NeurIPS paper shows — breadli428 · 2026-10-05