automated-proving

Tag

Cards List
#automated-proving

@omarsar0: Banger paper from Google Research on multi-agent proof discovery. (bookmark it) It's really interesting to see this eme…

X AI KOLs Timeline ↗ · 2026-10-02 Cached

Google Research presents Cogentic, a multi-agent harness built on Gemini that runs an iterative prove–verify loop to discover proofs for open problems in theoretical computer science, producing expert-verified novel results on five open problems in online learning, auction theory, and mechanism design.

0 favorites 0 likes
#automated-proving

EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery

arXiv cs.AI ↗ · 2026-09-02 Cached

EULER is a multi-agent system that explores cross-domain transfers to automatically prove or refute mathematical conjectures, validated with stress tests and evaluated on 120 recent conjectures, producing proofs, refutations, and partial results.

0 favorites 0 likes
#automated-proving

Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometry

arXiv cs.AI ↗ · 2026-08-18 Cached

Euclid-Omni is a neuro-symbolic framework integrating LLMs, VLMs, and a symbolic solver to address plane geometry problems from calculations to Olympiad-level proofs, using synthetic data generation for training.

0 favorites 0 likes
← Back to home

Submit Feedback