automated-reasoning

Tag

Cards List
#automated-reasoning

ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving

arXiv cs.AI · 2026-08-28 Cached

ProofEvolve is a neuro-symbolic framework that evolves formally verified proof structures using neural models to enhance automated theorem proving, achieving high solve rates on Lean benchmarks by preserving verified knowledge from incomplete attempts.

0 favorites 0 likes
#automated-reasoning

The Problem Is the Problem: Towards Scalable Mathematical Discovery

arXiv cs.AI · 2026-08-19 Cached

The paper introduces FAR, a human-AI discovery paradigm that automates the search for mathematical problems from literature, with a pilot in combinatorics demonstrating its effectiveness in identifying conjectures and resolutions.

0 favorites 0 likes
#automated-reasoning

Theo Conjecture solves 35-year-old math problem, finds a term no one predicted

Hacker News Top · 2026-07-29 Cached

An AI system called Theo Conjecture, leveraging a large language model, solved a 35-year-old graph theory problem originally posed by mathematician Paul Erdős, discovering an unexpected term. The system works by proposing, testing, and revising mathematical ideas in a loop.

0 favorites 0 likes
#automated-reasoning

Learned Interventions in Lean 4 grind

arXiv cs.LG · 2026-07-28 Cached

A research paper introducing a failure-triggered cascade approach to safely integrate machine learning into Lean 4's grind tactic, achieving improved efficiency and solving previously unsolvable proofs without regressions.

0 favorites 0 likes
#automated-reasoning

OpenProver: Agentic and Interactive Theorem Proving with Lean 4

arXiv cs.AI · 2026-07-13 Cached

OpenProver is an open-source system for LLM-driven automated theorem proving using Lean 4, featuring a Planner-Worker-Verifier architecture and both autonomous and interactive modes. It enables reproducible evaluation and human-AI synergy in mathematical proof search.

0 favorites 0 likes
#automated-reasoning

RMA: an Agentic System for Research-Level Mathematical Problems

arXiv cs.AI · 2026-05-25 Cached

Research Math Agents (RMA) is an agentic framework for automated reasoning on research-level mathematical problems, achieving state-of-the-art results on the First Proof benchmark by solving 8 out of 10 problems, outperforming strong baselines like GPT-5.2R and Aletheia.

0 favorites 0 likes
#automated-reasoning

Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics

arXiv cs.AI · 2026-05-14 Cached

This paper introduces Formal Conjectures, an evolving benchmark of 2615 mathematical statements formalized in Lean 4, including open research conjectures for proof discovery and solved problems for auto-formalization, designed to evaluate automated reasoning systems with zero contamination.

0 favorites 0 likes
← Back to home

Submit Feedback