arXiv cs.AI· Jonas Limniatis, Bennet Schaarmann, Georg Reuber, Robert Stahlbock·· 10 小时前AI 评分31
TIGA：用工具接地 LLM 智能体与运行时自适应策略实现受控知识工程的本体分类构建
Controlled Knowledge Engineering for Taxonomy Induction with Tool-Grounded LLM Agents and Runtime-Adaptive Policies
AI 导读
TIGA 将本体分类（taxonomy）构建形式化为基于显式状态与受限动作空间的迭代决策过程，结合可执行的分类编辑工具、记录工具调用与理由的交互记忆，以及智能体在推理中修订的运行时自适应组织策略。
正文 · 原文
Abstract:Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a fixed set of candidate entities requires more than plausible text generation: the resulting hierarchy must be complete, structurally valid, and semantically coherent. Large Language Models (LLMs) are promising for this task, but iterative free-form generation remains vulnerable to omitted or hallucinated entities, invalid hierarchical relations, and inconsistent organizational principles. We introduce TIGA (Taxonomy Induction with Tool-Grounded Agents), a knowledge-engineering architecture that formulates taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, an memory that records tool calls, rationales, and outcomes, and a runtime-adaptive organizational policy that the agent revises during inference. An optional global reviewer evaluates the constructed taxonomy against the candidate set and the active policy. We evaluate TIGA on four benchmark taxonomies using two LLM backbones and compare it with single-shot and iterative prompting-based baselines. TIGA achieves the strongest structural-quality results in most evaluated configurations, but does not dominate on every precision measure. The gains are accompanied by substantially higher token consumption, API-call volume, and inference time. Ablation results show consistent benefits from the policy and interaction-memory components, whereas the effect of global review depends on the dataset and the available revision budget. These findings characterize tool grounding and runtime policy adaptation as promising but costly mechanisms for improving the controlled construction of structured knowledge representations.
| Comments: | Submitted to Knowledge-Based Systems. Code: this https URL |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13966 [cs.IR] |
| (or arXiv:2611.13966v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13966 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jonas Limniatis [view email]
[v1]
Tue, 10 Nov 2026 12:04:54 UTC (3,676 KB)
来源：arXiv cs.AI · arxiv.org