A teacher-aware evolutionary method repurposes learned optimization policies as behavioral teachers to evolve better static heuristics for scheduling, routing, and graph problems, outperforming performance-only baselines without runtime neural costs.
Reevo: Large language models as hyper-heuristics with reflective evolution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Teacher-Aware Evolution of Heuristic Programs from Learned Optimization Policies
A teacher-aware evolutionary method repurposes learned optimization policies as behavioral teachers to evolve better static heuristics for scheduling, routing, and graph problems, outperforming performance-only baselines without runtime neural costs.