# Planning in the LLM Era: Building for Reliability and Efficiency

arXiv: https://arxiv.org/abs/2605.21902 · HTML: https://mlsanity.com/paper/2605.21902/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 15 of 15)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024)
- [Thought of Search: Planning with Language Models Through The Lens of Efficiency](https://mlsanity.com/paper/2404.11833/) (2024)
- [Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code](https://mlsanity.com/paper/2503.18809/) (2025)
- [Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts](https://mlsanity.com/paper/2409.15915/) (2024)
- [Compiling Uncertainty Away in Conformant Planning Problems with Bounded Width](https://mlsanity.com/paper/1401.3468/) (2014)
- [Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game](https://mlsanity.com/paper/2508.02900/) (2025)
- [Can LLMs Fix Issues with Reasoning Models? Towards More Likely Models for AI Planning](https://mlsanity.com/paper/2311.13720/) (2023)
- [Automating Thought of Search: A Journey Towards Soundness and Completeness](https://mlsanity.com/paper/2408.11326/) (2024)

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

- [Neurosymbolic Embodied Agents](https://mlsanity.com/paper/2608.16794/) (2026)

## Abstract (arXiv)

Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning relied on single-shot plan generation, followed by hybrid approaches that coupled LLMs with limited external search. These methods, unsound and incomplete by their very nature, often require substantial resources without yielding better solutions on unseen problems. As the limitations of LLMs become clearer, recent work has shifted toward using them at solution construction time -- generating symbolic solvers for a family of problems that can be verified and then used efficiently at inference time. This trend reflects the growing need for agents that are both reliable and resource-efficient. It also offers a path towards generating maintainable planners with minimal dependence on language models at inference time. In this paper, we argue that this shift reflects a broader realignment of the planning field in the LLM era. We examine three major categories of planner-generation methods, discuss their current limitations, and outline research steps towards a more reliable and efficient LLM-based generation of planners.