mlsanityData to 7 Oct 2026

Text-to-Stage: Spatial Layouts from Long-form Narratives

arXiv 2603.17832 ↗First posted 18 Mar 2026cs.CL cs.AI cs.LGcited by 0

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits many downstream media applications. Concretely, we study the narrative-to-play task: inferring stage-play layouts (scenes, speaker positions, movements, and room types) from text that lacks explicit spatial, positional, or relational cues. We then introduce a dramaturgy-inspired deterministic evaluation suite and, finally, a training and inference recipe that combines rejection SFT using Best-of-N sampling with RL from verifiable rewards via GRPO. Experiments on a text-only corpus of classical English literature demonstrate improvements over vanilla models across multiple metrics (character attribution, spatial plausibility, and movement economy), as well as alignment with an LLM-as-a-judge and subjective human preferences.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 16 of its 37 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

16 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts18 Apr

Other references · 15

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  3. 2018Image Generation from Scene Graphscited by 324
  4. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  5. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 104
  6. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 93
  7. 2025Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contaminationcited by 81
  8. 2021SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoningcited by 75
  9. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 59
  10. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  11. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  12. 2024LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Modelcited by 34
3 more
  1. 2020The Importance of Suppressing Domain Style in Authorship Analysiscited by 18
  2. 2022The Project Dialogism Novel Corpus: A Dataset for Quotation Attribution in Literary Textscited by 13
  3. 2024Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3cited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Stuck in the Matrix: Probing Spatial Reasoning in Large Language Models
  2. 2026SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
  3. 2026Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
  4. 2026Learning to Draw ASCII Improves Spatial Reasoning in Language Models
  5. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
  6. 2026Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
  7. 2024Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning
  8. 2024Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark