Adaptive Budget Allocation for Evolutionary Crossover
Implement an adaptive mechanism that dynamically allocates rollout budgets between mutation and crossover based on population diversity metrics.
Source paper
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
Generated by AI. The paper’s authors did not write these.
Implement an adaptive mechanism that dynamically allocates rollout budgets between mutation and crossover based on population diversity metrics.
Replace full-set validation in evolutionary prompt optimization with a dynamically updated active learning subset to reduce computational overhead.
Integrate a retrieval-augmented generation system into compiler-based feedback loops to supply relevant hardware manuals during code generation mutation.
This paper introduces GEPA (Genetic-Pareto), a prompt optimization algorithm for compound AI systems that outperforms Reinforcement Learning (RL) methods like GRPO. GEPA uses natural language reflection to mutate prompts based on execution traces and maintains a Pareto frontier of diverse candidates to avoid local optima, achieving higher performance with significantly fewer rollouts.
GEPA employs an evolutionary algorithm where 'Reflective Prompt Mutation' uses an LLM to analyze failure traces and propose improvements, while 'Pareto-based Candidate Selection' preserves population diversity by keeping prompts that excel on specific task subsets rather than just a single global best.