# Language Models as Higher-Order Planning Formalizers

arXiv: https://arxiv.org/abs/2603.23844 · HTML: https://mlsanity.com/paper/2603.23844/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 21 of its 78 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 21 of 21)

- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning](https://mlsanity.com/paper/2502.01100/) (2025)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models](https://mlsanity.com/paper/2503.18971/) (2025)
- [Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages](https://mlsanity.com/paper/2407.03321/) (2024)
- [On the Limit of Language Models as Planning Formalizers](https://mlsanity.com/paper/2412.09879/) (2024)
- [PROC2PDDL: Open-Domain Planning Representations from Texts](https://mlsanity.com/paper/2403.00092/) (2024)
- [LLMs Can Plan Only If We Tell Them](https://mlsanity.com/paper/2501.13545/) (2025)
- [Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning](https://mlsanity.com/paper/2509.13351/) (2025)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [Constructing Industrial-Scale Optimization Modeling Benchmark](https://mlsanity.com/paper/2602.10450/) (2026)
- [Kani: A Lightweight and Highly Hackable Framework for Building Language Model Applications](https://mlsanity.com/paper/2309.05542/) (2023)
- [Improved Generalized Planning with LLMs through Strategy Refinement and Reflection](https://mlsanity.com/paper/2508.13876/) (2025)
- [Enhancing LLM Planning Capabilities through Intrinsic Self-Critique](https://mlsanity.com/paper/2512.24103/) (2025)
- [Unifying Inference-Time Planning Language Generation](https://mlsanity.com/paper/2505.14763/) (2025)
- [Language Model as Planner and Formalizer under Constraints](https://mlsanity.com/paper/2510.05486/) (2025)

## Built on by (most cited first, 1 of 1)

- [SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning](https://mlsanity.com/paper/2610.11223/) (2026)

## Abstract (arXiv)

Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-Formalizers aim to address this by employing LLMs as a bridge to translate natural language descriptions into structured planning representations such as PDDL, which are then fed to a programmatic solver. We observe that its success may be overstated because planning problem descriptions in standard benchmarks often have a one-to-one mapping to PDDL, which departs from real use cases. To address this, we introduce the notion of unraveling problems where a natural yet succinct description translates into a very large PDDL representation. Using unraveling variants of four standard planning domains, we demonstrate that LLM Formalizers also do not always scale. We tackle this challenge by introducing a new paradigm, LLM-as-Higher-Order-Formalizer, where the LLM generates a high-level program that captures the recurrent logic within the description and in turn generates the larger PDDL representation. This decouples token output from the combinatorial explosion of the underlying formalization and search space, leading to improved performance for complex problems.