混合多智能体框架让电商对话推荐更可靠，严守商品库存限制。
MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation
- 用LLM理解用户需求，由专用代理严格执行库存筛选与约束检查
- 多轮对话中零偏差保持预算和排除项，排除反转成功率100%
- 适合需要高可靠性、不许虚构商品的电商平台部署
电商对话推荐日益依赖大语言模型，但实际应用常要求仅从商家固定商品库中推荐，禁止网络搜索或未经证实的产品陈述。核心挑战在于强约束下的可靠性：系统需满足用户需求、基于可用库存、并在多轮对话中持续维护偏好。本文提出MACS（多智能体商业系统），一种混合多智能体框架，在固定商品库场景下实现可靠对话推荐。MACS利用LLM处理语言任务如理解请求、挖掘偏好、生成回复，而产品检索、硬约束过滤、品牌排除、渐进式放宽等关键操作则由商家代理以确定性方式执行。会话持久化偏好层跨轮次跟踪约束，支持预算覆盖与排除项逆转的一致处理。在140个查询的单轮基准上，MACS达到最高通过率（87.1%）和完美品牌合规（1.000）。在10个场景的多轮基准上，其宏平均Pass@5达72%（优于GPT+Catalog的56%和Gemini+Catalog的52%），且无约束漂移。在排除项逆转（100%对20%/0%）和约束累积（100%对60%/40%）方面优势显著。人工评分响应质量相近（0.751对0.736）。结果表明，结合确定性约束执行与会话持久化偏好追踪的混合架构，在固定商品库场景下优于仅依赖提示的基线系统。
原文摘要 · Abstract (English)
Conversational recommendation for e-commerce is increasingly mediated by large language models (LLMs), yet many real-world deployments operate under a stricter requirement: recommendations must be drawn only from a merchant's fixed catalog, without web search or unsupported product claims. In this setting, the main challenge is reliability under hard constraints: the system must satisfy user requirements, remain grounded in available inventory, and preserve preferences across multiple conversational turns. We present MACS (Multi-Agent Commerce System), a hybrid multi-agent framework for reliable conversational recommendation in fixed-catalog settings. MACS uses LLMs for language-facing tasks such as interpreting user requests, eliciting preferences, and generating responses, while correctness-critical operations, including product retrieval, hard-constraint filtering, brand exclusion, and progressive relaxation, are executed deterministically by the merchant agent. A session-persistent preference layer tracks constraints across turns, enabling consistent handling of budget overwrites and exclusion reversals. On a 140-query single-turn benchmark, MACS achieves the highest pass rate (87.1%) and perfect brand compliance (1.000). On a 10-scenario multi-turn benchmark, MACS achieves the strongest macro Pass@5 (72% vs. 56% GPT+Catalog / 52% Gemini+Catalog) with zero constraint drift. The advantage is sharpest on exclusion reversal (100% vs. 20% / 0%) and constraint accumulation (100% vs. 60% / 40%). Mean judged response quality is similar across systems (0.751 vs. 0.736). These results suggest that hybrid architectures combining deterministic constraint enforcement with session-persistent preference tracking provide stronger reliability-oriented performance than catalog-bound prompt-only baselines in the fixed-catalog merchant setting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。