LLM-based agents in Lean solved 9 of 353 open Erdős problems and proved 44 of 492 OEIS conjectures at a few hundred dollars each.
Pawan Kumar, Emilien Dupont, Francisco J
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Squeeze Evolve is a multi-model orchestration framework that improves efficiency and performance in verifier-free evolutionary inference, cutting costs up to 3x while matching verifier-based methods on several benchmarks.
citing papers explorer
-
Advancing Mathematics Research with AI-Driven Formal Proof Search
LLM-based agents in Lean solved 9 of 353 open Erdős problems and proved 44 of 492 OEIS conjectures at a few hundred dollars each.
-
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Squeeze Evolve is a multi-model orchestration framework that improves efficiency and performance in verifier-free evolutionary inference, cutting costs up to 3x while matching verifier-based methods on several benchmarks.