Abstract:While researchers have made significant progress in enabling large language models (LLMs) to perform multi-step planning, LLMs struggle to ensure that those plans align with high-level user intent and satisfy symbolic constraints, especially in complex, multi-step domains. Existing reasoning approaches such as Chain-of-Thought (CoT), Tree-of-Thought (ToT), and verifier-augmented methods, expand the search space but often yield infeasible actions or hallucinated steps. To overcome these limitations, we propose Constraints-of-Thought (Const-o-T), a framework that provides a structured prior that enables Monte Carlo Tree Search (MCTS) focus search on semantically meaningful paths. Each reasoning step is represented as an (intent, constraint) pair, which serves both to compress the search space and enforce validity. Unlike prior methods that merely generate reasoning traces or validate outputs post hoc, Const-o-T uses (intent, constraint)pairs to actively focus the search toward feasible and meaningful plans. We integrate Const-o-T into MCTS using a structured representation of intent-constraint pairs constraints prune infeasible branches and guide exploration toward semantically valid actions, improving planning efficiency and verifiable decision-making. We demonstrate across three domains Risk game, CAD code generation, and arithmetic reasoning that our approach outperforms baselines, yielding higher accuracy and stronger structural alignment. Our contribution is to demonstrate that Const-of-T offers a generalizable foundation for constraint-guided reasoning, enabling more efficient, constraint-aligned, and domain-adaptable planning with LLMs.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.08992 [cs.LG] |
| (or arXiv:2510.08992v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.08992 arXiv-issued DOI via DataCite |
From: Kamel Alrashedy [view email]
[v1]
Fri, 10 Oct 2025 04:21:18 UTC (5,747 KB)
[v2]
Fri, 27 Mar 2026 22:20:44 UTC (6,243 KB)
[v3]
Tue, 12 May 2026 20:47:09 UTC (7,256 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。