智能体
arxiv.org ·
通过结构化知识树在 LLM 驱动的侦探游戏中强制叙事可靠性与认知节奏
论文提出结构化知识树架构配合三智能体 LLM 流水线，将知识检索、对话生成与回复校验分离，使虚拟嫌疑人仅披露当前叙事状态允许的信息。在可玩侦探游戏测试床 The Interrogation of Adrian Gale 上评估，报告关键幻觉减少 64.78% 并完全阻止过早叙事披露，但严格机械约束带来强制对话披露的可用性权衡。
AI推荐理由 arXiv 论文，作者提出结构化知识树加三智能体流水线（知识检索、对话生成、回复校验分离），用于侦探游戏审讯对话，控制虚拟嫌疑人只披露当前叙事状态允许的信息。摘要给出可验证量化结果：关键幻觉减少 64.78%，并完全阻止过早叙事披露；同时承认严格机械约束带来可用性权衡（强制对话披露）。新信息在于用结构化知识树约束 LLM 非确定性输出、实现认知节奏控制，对 LLM 游戏叙事与可控生成有参考价值；局限是仅在单一自建测试床 The Interrogation of Adrian Gale 上评估，未提供跨场景泛化证据。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.23043 (cs)
[Submitted on 19 Sep 2026]
Title:Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees
Authors:Parsa Rahmati, Richard Zhao
View a PDF of the paper titled Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees, by Parsa Rahmati and 1 other authors
View PDF
HTML (experimental)
Abstract:Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic outputs make it difficult to preserve authorial control, factual consistency, and the intended sequence of information disclosure. These challenges are particularly significant in detective games, where premature revelation or fabricated details can undermine the logic of player progression. We present a Structured Knowledge Tree architecture coupled with a tri-agent LLM pipeline for controlling dialogue in an open-ended interrogation game. The system separates knowledge retrieval, dialogue generation, and response verification to ensure that the virtual suspect reveals only information permitted by the current narrative state. We evaluate the approach through The Interrogation of Adrian Gale, a playable detective-game testbed, and a formal user study examining hallucination reduction, adherence to authored disclosure sequences, and perceived logical progression. Our results demonstrate that the structured architecture reduces critical hallucinations by 64.78% and entirely prevents premature narrative disclosure. While the strict mechanical constraints introduced usability trade-offs regarding forced conversational reveals, the system successfully enforces rigorous epistemic pacing and provides players with a clear, subjective sense of progression toward solving the case.
Comments:
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:
arXiv:2609.23043 [cs.AI]
(or
arXiv:2609.23043v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.23043
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Richard Zhao [view email]
[v1]
Sat, 19 Sep 2026 14:18:47 UTC (3,893 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees, by Parsa Rahmati and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)