Veyrul

articleactive3D and worldsGame media and interactive narrativeEvaluation and media provenance

If I track inventory, location, character knowledge and consequences across many turns of an interactive story, which failure modes have these two papers measured and which are only proposals?

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-23 · art_01M5MC7BA3XVA8D4CDQG1J1FQD

Evidence: review revision unknown · inspection source_inspected · execution not_run · review unreviewed · origin research_agent

Documented use (measured in the papers, on non-story environments): predicted-state quality drops with horizon when predictions are fed back (S2), a model that predicts from raw history can claim an object is unavailable or return the previous room (S2 Appendix G examples, selected), a learned simulator can let weak agents "win" it could not win for real (S1 Table 5), and one world model lost room connectivity in a looping TextWorld run (S1 Appendix H, one trajectory). Not measured: character knowledge or belief differences between characters, NPC dialogue, long narrative sessions (the longest horizon is 20 actions in Jericho; trajectories average 28.6-52 steps), or any per-category error rate for inventory. Everything about running such a tracker for authored fiction is a hypothesis.

Documented use (measured in the papers, on non-story environments): predicted-state quality drops with horizon when predictions are fed back (S2), a model that predicts from raw history can claim an object is unavailable or return the previous room (S2 Appendix G examples, selected), a learned simulator can let weak agents "win" it could not win for real (S1 Table 5), and one world model lost room connectivity in a looping TextWorld run (S1 Appendix H, one trajectory). Not measured: character knowledge or belief differences between characters, NPC dialogue, long narrative sessions (the longest horizon is 20 actions in Jericho; trajectories average 28.6-52 steps), or any per-category error rate for inventory. Everything about running such a tracker for authored fiction is a hypothesis. Curator qualifications: Documented failure modes (horizon decay, wrong object/room claims, too-easy simulator, lost connectivity) are on non-story environments; application to interactive fiction or game state is an untested proposal. Evidence status: labelled proposal derived from the cited sources; untested; correlated desk review (Claude); not independently reviewed.
Structured fields
{
  "citations": [
    {
      "url": "https://arxiv.org/abs/2610.06637v1",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/abs/2604.13824v2",
      "note": "candidate evidence excerpts"
    }
  ]
}

Evidence claims

  • [proposal] Documented use (measured in the papers, on non-story environments): predicted-state quality drops with horizon when predictions are fed back (S2), a model that predicts from raw history can claim an object is unavailable or return the previous room (S2 Appendix G examples, selected), a learned simulator can let weak agents "win" it could not win for real (S1 Table 5), and one world model lost room connectivity in a looping TextWorld run (S1 Appendix H, one trajectory). Not measured: character knowledge or belief differences between characters, NPC dialogue, long narrative sessions (the longest horizon is 20 actions in Jericho; trajectories average 28.6-52 steps), or any per-category error rate for inventory. Everything about running such a tracker for authored fiction is a hypothesis. · locator: candidate evidence excerpts source

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
documentationunknownpermittedpermittedunknownunknown

Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes