Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?
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_ | 1866909691275116544 |
|---|---|
| author | Zhang, Yanjian Wisniewski, Guillaume Tomeh, Nadi Charnois, Thierry |
| author_facet | Zhang, Yanjian Wisniewski, Guillaume Tomeh, Nadi Charnois, Thierry |
| contents | Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning challenges. In this work, we investigate whether prompting can control LLMs reasoning strategies and assess its impact on logical problem-solving. While our experiments show that no single strategy consistently improves accuracy, performance could be enhanced if models could adaptively choose the optimal strategy. We propose methods to guide LLMs in strategy selection, highlighting new ways to refine their reasoning abilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize? Zhang, Yanjian Wisniewski, Guillaume Tomeh, Nadi Charnois, Thierry Computation and Language Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning challenges. In this work, we investigate whether prompting can control LLMs reasoning strategies and assess its impact on logical problem-solving. While our experiments show that no single strategy consistently improves accuracy, performance could be enhanced if models could adaptively choose the optimal strategy. We propose methods to guide LLMs in strategy selection, highlighting new ways to refine their reasoning abilities. |
| title | Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.11423 |