Latest Research Papers
2025-01-17
arXiv
Evolving Deeper LLM Thinking
The paper introduces Mind Evolution, an evolutionary search strategy for scaling inference in Large Language Models, which outperforms other methods like Best-of-N and Sequential Revision in natural language planning tasks without the need for a formal solver.
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.