Evolving Deeper LLM Thinking
This addresses the challenge of improving LLM performance in natural language planning tasks without formal solvers, representing a strong specific gain in inference strategies.
The paper tackles the problem of scaling inference time compute in Large Language Models by proposing Mind Evolution, an evolutionary search strategy that generates, recombines, and refines candidate responses, resulting in solving over 98% of problem instances on TravelPlanner and Natural Plan benchmarks using Gemini 1.5 Pro.
We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.