Abstract:Graph of Thoughts (GoT), a generalized form of recent prompting paradigms for large language models (LLMs), has been shown to be useful for elaborate problem solving. By executing a graph of operations, thoughts of the LLM are structured as an arbitrary graph, forming the actual graph of thoughts. Originally, the graph of operations is defined manually, which requires in-depth knowledge about the solution of the problem to solve. Such a static graph of operations is rigid and therefore lacks adaptability. We propose Reinforced Graph of Thoughts (RGoT), an automated approach to the GoT prompting paradigm that leverages reinforcement learning (RL) to adaptively generate a graph of operations from a human-defined set. Results indicate that, under certain constraints, it is possible to construct graphs of operations adaptively to the task's complexity in an automated way.
| Comments: | 26 pages (including appendix), 16 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.22195 [cs.LG] |
| (or arXiv:2605.22195v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22195 arXiv-issued DOI via DataCite (pending registration) |
From: Manuel Noah Riesen [view email]
[v1]
Thu, 21 May 2026 09:00:16 UTC (342 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。