cs.AI提交于 2026-10-31已译

面向意图解释与服务发现的协商感知混合 LLM 框架

A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery

Wided Meflah · Hayet Brabra · Walid Gaaloul

中文摘要

用户越来越多地以自然语言意图而非结构化请求表达需求，这些意图可能不完整、层次过高或内部冲突。冲突意图要么违反云范式的基本属性，要么包含互不一致的需求。经典组合方法面向结构化、低层且完整的请求，无法解释此类意图、从提供商目录中发现合适服务，或与用户协商冲突需求。为此，提出一种协商感知的意图解释与服务发现框架：先精化自然语言意图并动态检测冲突，再将意图结构化为与提供商无关的 TOSCA 模板；对每个规格，通过基于云提供商产品的确定性匹配检索候选服务报价。部分冲突在解释阶段出现，另一些需求在发现阶段被证明不可满足，二者均通过迭代的自然语言协商与用户解决。在 70 个多样意图上与单次及增强提示基线对比评估，该框架提升了冲突检测与服务发现的召回率和 F1，消除了幻觉报价，并以与冲突数量成比例的成本解决冲突。

关键要点

01问题：自然语言意图常不完整或冲突，经典组合方法无法解释、发现服务或协商需求
02方法：先精化意图并检测冲突，再结构化为 TOSCA 模板，用确定性匹配检索候选服务报价
03方法：解释与发现阶段的冲突均通过迭代自然语言协商与用户解决
04结果：在 70 个意图上对比单次与增强提示基线，冲突检测和服务发现的召回率与 F1 均提升
05结果：消除幻觉报价，冲突解决成本与冲突数量成比例

解读

尚无解读。

原始英文摘要

arXiv:2610.40161v1 Announce Type: new Abstract: Increasingly, users express their needs as natural-language intents rather than structured requests. These intents may be incomplete, high-level, or internally conflicting. A conflicting intent either violates fundamental properties of the cloud paradigm or states mutually inconsistent requirements. Classical composition approaches are designed for structured, low-level, and complete requests. They cannot interpret such intents, discover suitable services from provider catalogs, or negotiate conflicting requirements with users. To address this gap, we propose a negotiation-aware framework for intent interpretation and service discovery. The framework first refines the natural-language intent and dynamically detects conflicts. It then structures the intent into a provider-independent TOSCA template. For each specification, it retrieves candidate service offers through deterministic matching grounded in cloud provider offerings. Some conflicts arise during interpretation. Other requirements prove unsatisfiable during discovery. Both are resolved through iterative natural-language negotiation with the user. We evaluate the framework on 70 diverse intents against single-shot and enhanced-prompting baselines. It improves recall and F1 for both conflict detection and service discovery. It also eliminates hallucinated offers and resolves conflicts at a cost proportional to their number.