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

DevFeed: [A Negotiation-Aware Hybrid LLM Framework for Intent Interpretation and Service Discovery](<https://devfeed.tech/articles/a-negotiation-aware-hybrid-llm-framework-for-intent-interpretation-and-service-discovery-107405.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.40161>)

Author: Wided Meflah, Hayet Brabra, Walid Gaaloul

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Emerging Cloud Service Models](<https://devfeed.tech/topics/emerging-cloud-service-models.md>)

Tags: [cloud](<https://devfeed.tech/tags/cloud.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [detection](<https://devfeed.tech/tags/detection.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [framework](<https://devfeed.tech/tags/framework.md>), [matching](<https://devfeed.tech/tags/matching.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [negotiation](<https://devfeed.tech/tags/negotiation.md>), [offers](<https://devfeed.tech/tags/offers.md>), [service-discovery](<https://devfeed.tech/tags/service-discovery.md>), [services](<https://devfeed.tech/tags/services.md>), [structured](<https://devfeed.tech/tags/structured.md>), [template](<https://devfeed.tech/tags/template.md>), [user](<https://devfeed.tech/tags/user.md>), [users](<https://devfeed.tech/tags/users.md>)

## AI overview

The framework turns incomplete or conflicting natural-language cloud requests into provider-independent TOSCA templates, then finds candidate offers by deterministic matching against provider catalogs. It uses iterative natural-language negotiation to resolve conflicts detected during interpretation and requirements that prove unsatisfiable during discovery. In an evaluation of 70 diverse intents, it improved recall and F1 for conflict detection and service discovery versus single-shot and enhanced-prompting baselines, eliminated hallucinated offers, and resolved conflicts at a cost proportional to their number. The excerpt does not provide metric values or further evaluation details.

## Source excerpt

arXiv:2610.40161v1 Announce Type: cross 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.