PulseAugur
EN
LIVE 12:03:16

LLMs used to build MaxSAT solver from research papers

By PulseAugur Editorial · [2 sources] ·

Researchers explored the use of large language models (LLMs) to construct a MaxSAT solver, named CoreForge, by interpreting research papers rather than relying on existing codebases. The iterative process involved discussions with ChatGPT, code generation via Codex prompts, and LLM-assisted code audits. While the LLM-assisted approach demonstrated potential in implementing solver components and passing evaluations, the resulting solver's performance did not match that of manually engineered solvers, highlighting the need for human oversight and external validation. AI

IMPACT Demonstrates LLMs' capability in complex code generation from research, though human oversight remains critical for performance.

RANK_REASON The cluster contains an academic paper detailing a research project and its findings.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

LLMs used to build MaxSAT solver from research papers

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Ruben Martins ·

    Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience

    arXiv:2607.14818v1 Announce Type: cross Abstract: We report on CoreForge, an experience in using large language models (LLMs) to build an unweighted MaxSAT solver from research papers rather than from an existing solver codebase. The project focuses on unsatisfiability-based MaxS…

  2. arXiv cs.AI TIER_1 English(EN) · Ruben Martins ·

    Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience

    We report on CoreForge, an experience in using large language models (LLMs) to build an unweighted MaxSAT solver from research papers rather than from an existing solver codebase. The project focuses on unsatisfiability-based MaxSAT algorithms and follows an iterative workflow th…

RELATED ENTITIES

RELATED TOPICS