Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement
cs.AI, cs.LG, cs.NA, math.NA
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/alan2326/proof-refinement
Terminology
Sources
- First Proof
- Remarks on the disproof of the unit distance conjecture
- The motivic class of the space of genus $0$ maps to the flag variety
- Eigenweights for arithmetic Hirzebruch Proportionality
- Aletheia tackles FirstProof autonomously
- Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erd\H{o}s Problems
- Towards Autonomous Mathematics Research
- Primal/Dual Method for the Grothendieck Constant
- Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline
- Point Convergence of Nesterov's Accelerated Gradient Method: An AI-Assisted Proof
- Automated Conjecture Resolution with Formal Verification
- ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
- The Grothendieck Constant is Less Than $\frac{\pi}{2 \log (1+ \sqrt{2})} - 10^{-5}$
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- New Lower and Upper Bounds for the Grothendieck Constant
- An explicit lower bound for the unit distance problem
- The Maximum Principle for the Bergman Space and the M\"obius Pseudodistance for the Annulus
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents