We embark on employing LLMs as optimizers, where the LLM progressively generates new solutions to optimize an objective function. Our evaluation demonstrates that LLMs have the capacity of gradually improving generated solutions based on the past optimization trajectory.
Interestingly, on small-scale traveling salesman problems, OPRO performs on par with some hand-crafted heuristic algorithms. This highlights the potential of LLMs in handling complex optimization problems effectively.
For prompt optimization, optimized prompts outperform human-designed prompts on GSM8K and Big-Bench Hard by a significant margin, sometimes over 50%. This indicates that LLMs can significantly enhance optimization strategies.
A number of unresolved questions are open for future research on LLMs for optimization, especially regarding how to reduce the sensitivity to initialization and balance exploration versus exploitation.
[
Collection
]
[
|
...
]