Pith.

Artificial Intelligence · arXiv:2512.23676 v2 · submitted 29 Dec 2025

Web World Models

Jichen Feng, Yifan Zhang, Chenggong Zhang, Yifu Lu, Shilong Liu, Mengdi Wang

The paper says

“Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments.”

from the abstract · picked out as the main claim by a classifier

Pith says

Pith has not reviewed this paper.

Get a Pith Review, $5

Reviews

Reviews by people

No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully generative world models aim for unlimited environments, but the world is constructed primarily through generation, making it harder to maintain a fixed, deterministic global framework and reducing controllability. In this work, we introduce the Web World Model (WWM), a middle ground where world state and “physics” are implemented in ordinary web code to ensure logical consistency, while large language models generate context, narratives, and high-level decisions on top of this structured latent state. We build a suite of WWMs on a realistic web stack, including an infinite travel atlas grounded in real geography, fictional galaxy explorers, web-scale encyclopedic and narrative worlds, and simulation- and game-like environments. Across these systems, we identify practical design principles for WWMs: separating code-defined rules from model-driven imagination, representing latent state as typed web interfaces, and utilizing deterministic generation to achieve unlimited but structured exploration. Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments.

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-10 · no language-model review

How the main claim is stated: hedged possibility 1.00

What the abstract itself states, as probabilities: claims first 0.08 · states limitation 0.17 · human participants 0.06 · controlled comparison 0.11 · randomized assignment 0.01 · states quantitative result 0.03 · compares with prior results 0.82 · mentions code or data availability 0.07

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v2). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Language agents increasingly require persistent worlds in which they can act, remember, and learn. background 1.00 0.04 0.03 asserted 0.98
Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully generative world models aim for unlimited environments, but the world is constructed primarily through generation, making it harder to maintain a fixed, deterministic global framework and reducing controllability. background 0.74 0.05 0.04 asserted 1.00
In this work, we introduce the Web World Model (WWM), a middle ground where world state and ``physics'' are implemented in ordinary web code to ensure logical consistency, while large language models generate context, narratives, and high-level decisions on top of this structured latent state. contribution 0.90 0.82 0.16 asserted 1.00
We build a suite of WWMs on a realistic web stack, including an infinite travel atlas grounded in real geography, fictional galaxy explorers, web-scale encyclopedic and narrative worlds, and simulation- and game-like environments. contribution 0.84 0.95 0.05 asserted 1.00
Across these systems, we identify practical design principles for WWMs: separating code-defined rules from model-driven imagination, representing latent state as typed web interfaces, and utilizing deterministic generation to achieve unlimited but structured exploration. contribution 0.53 0.92 0.13 asserted 1.00
Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments. interpretation 0.98 0.87 0.85 hedged possibility 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from simulation or computation 0.37

What was examined, and what was not

Sources read

  • arXiv listing abstract v2

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-10: 1 request, 5,083 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

How the literature uses it

10 arXiv papers cite this in 18 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 14 sentences without a confident label

Cites it as support 1 paper
  • Programmatic generators provide controllable and verifiable rule scaffolds, while learned world models and content generation can enrich interaction experience at scale, including by embedding model calls inside executable scaffolds [ref] .

    Scalable Environments Drive Generalizable Agents · Alternative Views · 0.96

Cites it as background 3 papers

Challenges and discussion

Know something about this paper? Leave a comment.

No comments yet.

Sign in to comment