An LLM multi-agent framework with a structured solver refactoring automatically improves pseudo-Boolean optimization local search heuristics, outperforming the authors' NuPBO-based baseline and rivaling Gurobi on several benchmarks.
In ECAI 2023, 1124–1131
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
An LLM multi-agent framework with a structured solver refactoring automatically improves pseudo-Boolean optimization local search heuristics, outperforming the authors' NuPBO-based baseline and rivaling Gurobi on several benchmarks.