{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2025-05-14-alphaevolve/","md":"https://postcutoff.com/e/2025-05-14-alphaevolve/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2025-05-14-alphaevolve","date":"2025-05-14","date_precision":"day","short_title":"AlphaEvolve: Gemini-powered agent discovers new algorithms","deck":null,"takeaway":"Google DeepMind's AlphaEvolve combined Gemini models with evolutionary search and automated evaluation to discover new algorithms, including a way to multiply 4×4 complex matrices with 48 scalar multiplications, improving on Strassen's 1969 algorithm.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms (Google DeepMind)","url":"https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/","type":"official","group":"primary","domain":"deepmind.google"},{"n":2,"title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery (arXiv)","url":"https://arxiv.org/abs/2506.13131","type":"paper","group":"primary","domain":"arxiv.org"},{"n":3,"title":"Independent verification of the 48-multiplication algorithm (GitHub)","url":"https://github.com/PhialsBasement/AlphaEvolve-MatrixMul-Verification","type":"code","group":"primary","domain":"github.com"},{"n":4,"title":"Human follow-up: 48 multiplications with rational coefficients (arXiv 2506.13242)","url":"https://arxiv.org/abs/2506.13242","type":"paper","group":"primary","domain":"arxiv.org"}],"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind"],"title":"AlphaEvolve: Gemini-powered agent discovers new algorithms","summary":"Google DeepMind's AlphaEvolve combined Gemini models with evolutionary search and automated evaluation to discover new algorithms, including a way to multiply 4×4 complex matrices with 48 scalar multiplications, improving on Strassen's 1969 algorithm.","key_facts":["Announced 14 May 2025","4×4 complex-valued matrix multiplication with 48 scalar multiplications","Matched state of the art on ~75% and improved on ~20% of 50+ open math problems tested, per DeepMind","A scheduling heuristic recovers on average 0.7% of Google's worldwide compute resources","Kissing number in 11 dimensions: lower bound raised from 592 to 593","The 48-multiplication result is for complex-valued, non-commutative 4×4 multiplication; a June 2025 human follow-up gave a 48-multiplication scheme with rational coefficients (arXiv 2506.13242)","Nov 2025: Georgiev, Gómez-Serrano, Tao and Wagner applied AlphaEvolve to 67 problems (see related entry)"],"key_numbers":[],"tags":["algorithms","math","agents","evolutionary-search"],"science":{"field":"mathematics","subfield":"combinatorics / algorithms / geometry","problem":"4×4 complex matrix multiplication (Strassen 1969: 49 multiplications); kissing number in 11 dimensions; ~50 open problems","result":"48 scalar multiplications for 4×4 complex matrices; kissing configuration of 593 spheres in 11D (previous 592); matched SOTA on ~75% and improved ~20% of 50+ problems.","open_since":"1969","ai_system":["AlphaEvolve","Gemini 2.0 Flash","Gemini 2.0 Pro"],"human_role":"Humans define the problem and an automated scorer; evolutionary LLM search autonomous","verification":{"key":"expert","label":"Expert-checked","text":"Constructions verified computationally (independent GitHub checks); white paper, later arXiv"},"status":"confirmed","shock":"The first improvement on Strassen's 4×4 complex case in 56 years came from a general-purpose coding agent, not a specialised system like AlphaTensor."},"body_md":"## What happened\n\nDeepMind described an agent that iteratively writes and evaluates code, already deployed across Google's data centers, chip design and AI training.\n\n## Why it matters\n\nA concrete example of LLM-based systems making novel discoveries and improving the infrastructure that trains them — an early form of recursive improvement.","disputed":[],"related":[{"id":"2025-11-05-alphaevolve-tao-67-problems","url":"https://postcutoff.com/e/2025-11-05-alphaevolve-tao-67-problems/","date":"2025-11-05","date_precision":"day","short_title":"Tao, Gómez-Serrano, Georgiev and Wagner test AlphaEvolve on 67 maths problems","deck":null,"takeaway":"Coming from Tao, it gave the maths community a credible, balanced picture of what AI search could do, just before the 2026 surge.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-10-19","orgs":["Google DeepMind","UCLA","Brown University"]},{"id":"2024-07-25-alphaproof-imo-silver","url":"https://postcutoff.com/e/2024-07-25-alphaproof-imo-silver/","date":"2024-07-25","date_precision":"day","short_title":"AlphaProof and AlphaGeometry 2 reach IMO silver-medal standard","deck":null,"takeaway":"First AI to reach medal level at the IMO; a year later, natural-language LLMs reached gold.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":3,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind"]},{"id":"2023-12-14-funsearch-cap-sets","url":"https://postcutoff.com/e/2023-12-14-funsearch-cap-sets/","date":"2023-12-14","date_precision":"day","short_title":"FunSearch: an LLM finds new cap-set constructions, the first LLM discovery in open maths","deck":null,"takeaway":"It was the direct ancestor of AlphaEvolve and showed that LLMs' mistakes don't matter when outputs can be automatically checked.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google DeepMind","University of Wisconsin–Madison"]},{"id":"2022-10-05-alphatensor-matrix-multiplication","url":"https://postcutoff.com/e/2022-10-05-alphatensor-matrix-multiplication/","date":"2022-10-05","date_precision":"day","short_title":"AlphaTensor discovers faster matrix multiplication algorithms, beating Strassen's 1969 record for 4×4 mod 2","deck":null,"takeaway":"It was the first AI-found improvement to a famous algorithmic record.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":3,"official":2,"filed":"2026-09-29","updated":"2026-09-29","orgs":["DeepMind"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"edit","text":"Added science block, kissing-number fact, verification links"},{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":"https://postcutoff.com/s/alphaevolve-gemini-powered-agent"}