Language Model as Planner and Formalizer under Constraints

ACL ARR 2026 January Submission6920 Authors

Keywords: applications, code models, LLM/AI agents, neurosymbolic approaches, scaling, robustness

Abstract: LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning domain and problem in a formal language that can derive plans deterministically. However, both lines of work rely on standard benchmarks that only include generic and simplistic environmental specifications, leading to potential overestimation of the planning ability of LLMs and safety concerns in downstream tasks. We bridge this gap by augmenting widely used planning benchmarks with manually annotated, fine-grained, and rich natural language constraints spanning four formally defined categories. Over 4 state-of-the-art reasoning LLMs, 4 formal languages, and 4 datasets, we show that the introduction of one-sentence constraints consistently halves performance, indicating current LLMs' lack of robustness and avenue for future research.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: applications, code models, LLM/AI agents, neurosymbolic approaches, scaling, robustness

Contribution Types: Model analysis & interpretability, Data resources

Languages Studied: English, PDDL, LTL

Submission Number: 6920