mlsanityData to 7 Oct 2026

Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives

arXiv 2605.02475 ↗First posted 4 May 2026cs.AI cs.CLcited by 0

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns a narrative into a versioned graphical world model and lets two engines act on it: a causal physics grounded in Pearl's ladder of causation and a recently proposed counterfactual calculus over Ancestral Multi-World Networks; and a narrative physics that scores the same graph against four structural reader-states -- mystery, dramatic irony, suspense, and surprise -- in the tradition of Sternberg's curiosity/suspense/surprise triad, with suspense formalised in the structural-affect line of work on story comprehension and computational suspense. Large language models are used only at the boundary: extraction, rendering, and audit; identification, intervention, and counterfactual reasoning are carried out in typed code over the graph. The system is offered as a research artefact rather than as a benchmarked NLP model; code, fixtures, and pipeline are released open source.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 12 of its 124 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

12 of 124 references.

References · 12

  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  4. 2024A Survey on LLM-as-a-Judgecited by 1,384
  5. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causalitycited by 348
  6. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 162
  7. 2024SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMscited by 51
  8. 2024Echoes in AI: Quantifying lack of plot diversity in LLM outputscited by 47
  9. 2024Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Modelscited by 45
  10. 2021Nested Counterfactual Identification from Arbitrary Surrogate Experimentscited by 38
  11. 2022DOC: Improving Long Story Coherence With Detailed Outline Controlcited by 11
  12. 2022Great Expectations: Unsupervised Inference of Suspense, Surprise and Salience in Storytellingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
  2. 2023CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
  3. 2026Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives
  4. 2024Failure Modes of LLMs for Causal Reasoning on Narratives
  5. 2025Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
  6. 2026Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction
  7. 2025PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts
  8. 2026Planning Beyond Text: Graph-based Reasoning for Complex Narrative Generation