Atom of Thoughts for Markov LLM Test-Time Scaling
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_ | 1866917170785550336 |
|---|---|
| author | Teng, Fengwei Shi, Quan Yu, Zhaoyang Zhang, Jiayi Luo, Yuyu Wu, Chenglin Guo, Zhijiang |
| author_facet | Teng, Fengwei Shi, Quan Yu, Zhaoyang Zhang, Jiayi Luo, Yuyu Wu, Chenglin Guo, Zhijiang |
| contents | Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to the accumulation of historical dependency information during inference. To address this challenge, we leverage the memoryless property of Markov processes to minimize reliance on historical context and propose a Markovian reasoning process. This foundational Markov chain structure enables seamless integration with various test-time scaling methods, thereby improving their scaling efficiency. By further scaling up the Markovian reasoning chain through integration with techniques such as tree search and reflective refinement, we uncover an emergent atomic reasoning structure, where reasoning trajectories are decomposed into a series of self-contained, low-complexity atomic units. We name this design Atom of Thoughts (\our). Extensive experiments demonstrate that \our consistently outperforms existing baselines as computational budgets increase. Importantly, \our integrates seamlessly with existing reasoning frameworks and different LLMs (both reasoning and non-reasoning), facilitating scalable, high-performance inference.We submit our code alongside this paper and will make it publicly available to facilitate reproducibility and future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12018 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Atom of Thoughts for Markov LLM Test-Time Scaling Teng, Fengwei Shi, Quan Yu, Zhaoyang Zhang, Jiayi Luo, Yuyu Wu, Chenglin Guo, Zhijiang Computation and Language Artificial Intelligence Machine Learning Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to the accumulation of historical dependency information during inference. To address this challenge, we leverage the memoryless property of Markov processes to minimize reliance on historical context and propose a Markovian reasoning process. This foundational Markov chain structure enables seamless integration with various test-time scaling methods, thereby improving their scaling efficiency. By further scaling up the Markovian reasoning chain through integration with techniques such as tree search and reflective refinement, we uncover an emergent atomic reasoning structure, where reasoning trajectories are decomposed into a series of self-contained, low-complexity atomic units. We name this design Atom of Thoughts (\our). Extensive experiments demonstrate that \our consistently outperforms existing baselines as computational budgets increase. Importantly, \our integrates seamlessly with existing reasoning frameworks and different LLMs (both reasoning and non-reasoning), facilitating scalable, high-performance inference.We submit our code alongside this paper and will make it publicly available to facilitate reproducibility and future research. |
| title | Atom of Thoughts for Markov LLM Test-Time Scaling |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.12018 |