{"version":1,"type":"story","url":"https://digestai.news/story/specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency","json":"https://digestai.news/story/specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency.json","markdown":"https://digestai.news/story/specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency.md","slug":"specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency","headline":"SpecEvo reduces API cost by up to 80% and improves discovery efficiency","summary":"Researchers present SpecEvo, a multi‑LLM framework that orchestrates lightweight and frontier models for scientific discovery. Lightweight models act as parallel Speculators that generate and refine candidate programs, while an Advisor consolidates successes, failures, and saturated directions into ongoing guidance. At occasional checkpoints, a frontier‑model Navigator reviews the population and intervenes with synthesis, surgical refinement, or reframing when progress stalls.\n\nAcross 176 tasks in four scientific and algorithmic discovery domains, SpecEvo matches or outperforms frontier‑model baselines, cuts API cost by up to 80%, achieves up to 1.5x greater evaluation efficiency on equation discovery, and improves over the strongest CO‑Bench baseline by 3.8%. The authors argue that coordinating models by trajectory‑conditioned roles can make large‑scale discovery more cost‑effective.","keyPoints":["SpecEvo coordinates lightweight Speculators, an Advisor, and a frontier‑model Navigator for scientific search","On 176 tasks across four domains, it reduces API cost by up to 80% and boosts evaluation efficiency up to 1.5x","Performance exceeds the strongest CO‑Bench baseline by 3.8% while matching frontier‑model baselines"],"whyItMatters":"Demonstrates that strategic model coordination can lower compute expenses while maintaining or improving discovery performance, a key concern for research labs and enterprises scaling AI‑driven science.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["SpecEvo","CO-Bench"],"people":[]},"firstPublishedAt":"2026-10-22T04:00:00Z","updatedAt":"2026-10-22T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery","url":"https://arxiv.org/abs/2610.28706","publishedAt":"2026-10-22T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"SpecEvo reduces API cost by up to 80% and improves discovery efficiency\", 22 October 2026, https://digestai.news/story/specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency","publisher":"Digest AI","title":"SpecEvo reduces API cost by up to 80% and improves discovery efficiency","datePublished":"2026-10-22T04:00:00Z","url":"https://digestai.news/story/specevo-reduces-api-cost-by-up-to-80-and-improves-discovery-efficiency"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}