Agent Completes Rigorous Mathematical Proofs
kevrussell · x · 2026-07-10
The post describes rigorous proof results on two autocorrelation problems: it marginally improved the known public upper bound on 1-AC, which was achieved by constructing and certifying a massive continuous witness. For 2-AC, the post claims the system rigorously proved that the current leading solution has reached the theoretical limit.
More from Research
- Project APE launches CRED to test whether LLMs can verify research errors — soumitrashukla9 · 2026-07-22
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22