Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search
This addresses the issue of infeasible or hallucinated plans in LLM-guided search for users in complex, multi-step domains, offering a generalizable but incremental improvement over existing reasoning methods.
The paper tackled the problem of large language models (LLMs) struggling to align multi-step plans with user intent and symbolic constraints, proposing the Constraints-of-Thought (Const-o-T) framework to improve planning efficiency and verifiable decision-making, resulting in higher accuracy and stronger structural alignment across domains like Risk game, CAD code generation, and arithmetic reasoning.
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.