llm-kb
← Back to research
Paper

ProofCouncil: An LLM Agent for Solving Open Mathematical Problems

Researchers introduced ProofCouncil, an LLM agent with an author-critic architecture designed to solve open mathematical problems. It was submitted to the FirstProof challenge, where it autonomously tackled 6 out of 10 problems and received referee evaluations.

0 engagement·1 source·Fri, Jul 10, 2026, 02:46 PM
ProofCouncil is a mathematical agent that uses an author-critic workflow to address open problems. It participated in the second batch of FirstProof, a challenge consisting of 10 real-world mathematical problems that agents must solve autonomously. The agent's submissions for 6 of the 10 problems were judged by referees, demonstrating the potential of LLM-based agents in advanced mathematical reasoning.

Entities

ProofCouncil(tool)FirstProof(benchmark)

Related

Tool ReleaseFri, Jul 10, 2026, 09:07 AM

OpenProver: Open-source LLM-driven theorem proving with Lean 4 verification

OpenProver is an open-source system for LLM-driven automated theorem proving (ATP) that integrates Lean 4 formal verification. It uses a Planner-Worker-Verifier architecture to decompose mathematical problems into parallel workers, with a whiteboard scratchpad and repository for intermediate findings. The system is fully open-source and offers reproducible evaluation through automatic formal verification of generated proofs.

0 engagement·1 source·arxiv
arXiv
Tool ReleaseTue, Jul 7, 2026, 02:44 AM

Danus: open-source framework for mathematical reasoning with fact-graph memory

Danus is a new open-source framework that orchestrates mathematical reasoning agents using a fact-graph memory system. A main agent (Claude Code) directs a swarm of autonomous codex workers to prove statements, with a cold-start verifier as the sole authority on correctness. Verified results accumulate in a content-addressed fact graph, and a strategy loop decomposes problems and steers the swarm.

68 engagement·1 source·github
ProductSun, Jul 12, 2026, 09:39 AM

Local-first coding agent for long autonomous runs

Grinta is a local-first coding agent designed for long autonomous runs. It uses LLMs to autonomously plan and execute coding tasks, solving the problem of needing constant human supervision for extended development sessions.

1 engagement·1 source·hackernews
BreakthroughfeaturedFri, Jul 10, 2026, 06:29 PM

GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture

On July 10, 2026, a user on X (__eknight__) shared a PDF hosted on OpenAI's CDN containing a prompt that led GPT-5.6 Sol Ultra to produce a proof of the Cycle Double Cover Conjecture, a long-standing open problem in graph theory. The post on Hacker News garnered 755 points, indicating significant community interest. The prompt and resulting proof are available via OpenAI's CDN link.

755 engagement·1 source·hackernews
PaperFri, Jul 10, 2026, 08:39 AM

Hypothesis Evolution Protocol proposed for auditable AI scientist agents

A new arXiv paper introduces the Hypothesis Evolution Protocol (HEP), a framework to make LLM-based AI scientists auditable by structuring hypothesis generation, testing, and belief updates in a transparent, logged process. The protocol aims to address the lack of auditability in current autonomous scientific agents.

0 engagement·1 source·arxiv
arXiv