LLMs and Wilf-Zeilberger method combine for automated combinatorial proofs

Researchers have developed WZ-LLM, a novel neuro-symbolic framework that combines the Wilf-Zeilberger (WZ) method with large language models (LLMs) to automate formal proofs of combinatorial identities. This approach translates WZ proof plans into executable sketches in Lean 4, leveraging an LLM-based prover for subgoals. Experiments demonstrate that WZ-LLM achieves a 34% success rate on the LCI-Test dataset, surpassing existing methods like DeepSeek-V3 and Goedel-Prover-V2. AI

IMPACT This research could accelerate formal verification in mathematics and computer science by improving automated theorem proving capabilities.

RANK_REASON This is a research paper detailing a new method for automated formal proofs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• CombiBench
• DeepSeek-V3
• Goedel-Prover-V2
• LCI-Test
• LLM
• PutnamBench-Comb
• Wilf-Zeilberger
• WZ-LLM

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →