SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.03396 · 2026

Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation

Bryan Plummer, Kate Saenko, Maan Qraitem

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2601.03396.json · badge: /api/ran/2601.03396.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mqraitem/Persona-Weaver canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
collect_filler_stats Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/plot_fillers.py
pointer only (licence: NONE) · get_code("9c0506fdf3dda127")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

count_fillers Ran
ran, honoured the contract we drafted
mqraitem/Persona-Weaver/plot_fillers.py
pointer only (licence: NONE) · get_code("f53679ea1fe1fc3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_combinations Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/generate_personaweaver_interaction.py
pointer only (licence: NONE) · get_code("ec4365197be9e10e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_gen Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/generate_worldweaver.py
pointer only (licence: NONE) · get_code("a90e65678c92eb90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_moral_positions Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/generate_personaweaver_moral.py
pointer only (licence: NONE) · get_code("81a36a6fb2166bb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_persona_cards Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/get_answers_interaction.py
pointer only (licence: NONE) · get_code("e5f704cd313d538d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_persona_cards Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/get_answers_moral.py
pointer only (licence: NONE) · get_code("dc30c87806dc53f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_reaction_categories Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/generate_personaweaver_interaction.py
pointer only (licence: NONE) · get_code("33a795600256f1a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_combinations Ran
ran; our contract draft was wrong, not the code
mqraitem/Persona-Weaver/generate_personaweaver_interaction.py
pointer only (licence: NONE) · get_code("08264bcbd8a81114")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mqraitem/Persona-Weaver when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignment-induced biases in existing methods: a positive moral bias, where characters uniformly adopt agreeable stances (e.g., always saying lying is bad), and a helpful assistant bias, where characters invariably answer questions directly (e.g., never refusing or deflecting). While such tendencies suit instruction-following systems, they suppress dramatic tension and yield predictable characters, stemming from maximum likelihood training and assistant fine-tuning. To address this, we introduce PersonaWeaver, a framework that disentangles world-building (roles, demographics) from behavioral-building (moral stances, interactional styles), yielding characters with more diverse reactions and moral stances, as well as second-order diversity in stylistic markers like length, tone, and punctuation. Code: https: //github.com/mqraitem/Persona-Weaver

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.03396")
get_code_for_paper("2601.03396")
have("2601.03396")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2601.03396.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2601.03396.svg)](https://syntology.ai/paper/2601.03396)

Connect an agent — have() is free.