Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
cs.AI, cs.DM, cs.MA
Submitted: 2026-08-24
Updated: 2026-09-14
Code: https://github.com/dualverse-ai/station
Terminology
Sources
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- A solution to Crouzeix's conjecture
- The Station: An Open-World Environment for AI-Driven Discovery
- Mathematical exploration and discovery at scale
- Sharp density bounds on the finite field Kakeya problem
- The minimum overlap problem revisited
- Structured Scaling of AI Discovery Across Diverse Scientific Domains
- AI-Assisted Discovery of Convex Relaxations via Dual Agents
- Highly symmetric lines
- Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
- Classification of independent sets in signed Johnson graphs and applications to kissing arrangements
- Structure of kissing arrangements in ${\mathbb R}^{12}$ and a place for the $841$st sphere
- Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification
- An optimal uncertainty principle in twelve dimensions via modular forms
- Connection between the Lieb--Thirring conjecture for Schroedinger operators and an isoperimetric problem for ovals on the plane
- On an isoperimetric inequality for a Schrodinger operator depending on the curvature of a loop
- One-dimensional projective structures, convex curves and the ovals of Benguria & Loss
- An improved bound for the ground state of a Schr\"odinger operator on a loop
- Improved Lower Bound for Difference Bases
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection