Metraipolis › archive › dc_ffedf3b4108c

MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation — arXiv:2608.14068

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14068
License (as archived)
CC0-1.0
Archived
2026-10-19T02:21:18.531Z
SHA-256 of the archived text
9c878decfcb3b0e16d34d623ff741e2aa83f7f5aeda59d578c4f6b9ffe7e9915
Stable URL of this page
https://metraipolis.com/documento/dc_ffedf3b4108c

How to cite

MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation — arXiv:2608.14068 — arXiv (en), https://arxiv.org/abs/2608.14068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffedf3b4108c (Metraipolis archive dc_ffedf3b4108c, sha256 9c878decfcb3b0e16d34d623ff741e2aa83f7f5aeda59d578c4f6b9ffe7e9915)
BibTeX
@misc{dcffedf3b4108c,
  title = {MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation — arXiv:2608.14068},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14068},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffedf3b4108c; sha256 9c878decfcb3b0e16d34d623ff741e2aa83f7f5aeda59d578c4f6b9ffe7e9915},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14068 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:02:02.902Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).