Evolving Deeper LLM Thinking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912192003047424 |
|---|---|
| author | Lee, Kuang-Huei Fischer, Ian Wu, Yueh-Hua Marwood, Dave Baluja, Shumeet Schuurmans, Dale Chen, Xinyun |
| author_facet | Lee, Kuang-Huei Fischer, Ian Wu, Yueh-Hua Marwood, Dave Baluja, Shumeet Schuurmans, Dale Chen, Xinyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evolving Deeper LLM Thinking Lee, Kuang-Huei Fischer, Ian Wu, Yueh-Hua Marwood, Dave Baluja, Shumeet Schuurmans, Dale Chen, Xinyun Artificial Intelligence 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. |
| title | Evolving Deeper LLM Thinking |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2501.09891 |