# Plansformer: Generating Symbolic Plans using Transformers Source: [Plansformer: Generating Symbolic Plans using Transformers]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:53:04.613Z Authors: Vishal Pallagani, Bharath Muppasani, Keerthiram Murugesan, Francesca Rossi, Lior Horesh, Biplav Srivastava, Francesco Fabiano, Andrea Loreggia Published: 2022-12-16T19:06:49.000Z ## Abstract Large Language Models (LLMs) have been the subject of active research, significantly advancing the field of Natural Language Processing (NLP). From BERT to BLOOM, LLMs have surpassed state-of-the-art results in various natural language tasks such as question answering, summarization, and text generation. Many ongoing efforts focus on understanding LLMs' capabilities, including their knowledge of the world, syntax, and semantics. However, extending the textual prowess of LLMs to symbolic reasoning has been slow and predominantly focused on tackling problems related to the mathematical field. In this paper, we explore the use of LLMs for automated planning - a branch of AI concerned with the realization of action sequences (plans) to achieve a goal, typically executed by intelligent agents, autonomous robots, and unmanned vehicles. We introduce Plansformer; an LLM fine-tuned on planning problems and capable of generating plans with favorable behavior in terms of correctness and length with reduced knowledge-engineering efforts. We also demonstrate the adaptability of Plansformer in solving different planning domains with varying complexities, owing to the transfer learning abilities of LLMs. For one configuration of Plansformer, we achieve ~97% valid plans, out of which ~95% are optimal for Towers of Hanoi - a puzzle-solving domain. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Generalized Planning on Blocks (val)](): Generalized Planning; Blocks (val); Coverage: 100. - [Generalized Planning on Blocks (Interpolation)](): Generalized Planning; Blocks (Interpolation); Coverage: 100. - [Generalized Planning on Logistics (Extrapolation)](): Generalized Planning; Logistics (Extrapolation); Coverage: 0. - [Generalized Planning on Logistics (val)](): Generalized Planning; Logistics (val); Coverage: 0. - [Generalized Planning on Blocks (Extrapolation)](): Generalized Planning; Blocks (Extrapolation); Coverage: 10. - [Generalized Planning on Gripper (Extrapolation)](): Generalized Planning; Gripper (Extrapolation); Coverage: 0. - [Generalized Planning on Gripper (val)](): Generalized Planning; Gripper (val); Coverage: 0. - [Generalized Planning on Gripper (Interpolation)](): Generalized Planning; Gripper (Interpolation); Coverage: 0. - [Generalized Planning on VisitAll (Extrapolation)](): Generalized Planning; VisitAll (Extrapolation); Coverage: 0. - [Generalized Planning on VisitAll (val)](): Generalized Planning; VisitAll (val); Coverage: 0. - [Generalized Planning on Logistics (Interpolation)](): Generalized Planning; Logistics (Interpolation); Coverage: 0. - [Generalized Planning on VisitAll (Interpolation)](): Generalized Planning; VisitAll (Interpolation); Coverage: 0. ## Original sources and implementation [Original paper]() [PDF]()