Metraipolis › archive › dc_57609dca01f6
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation — arXiv:2611.05319
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05319
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:37:37.914Z
- SHA-256 of the archived text
e816de5e9e471fd9d97ffb7bb1fd060b934dddc42a88e9ba26591d0590d29dbb- Stable URL of this page
https://metraipolis.com/documento/dc_57609dca01f6
How to cite
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation — arXiv:2611.05319 — arXiv (en), https://arxiv.org/abs/2611.05319 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57609dca01f6 (Metraipolis archive dc_57609dca01f6, sha256 e816de5e9e471fd9d97ffb7bb1fd060b934dddc42a88e9ba26591d0590d29dbb)
BibTeX
@misc{dc57609dca01f6,
title = {HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation — arXiv:2611.05319},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05319},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57609dca01f6; sha256 e816de5e9e471fd9d97ffb7bb1fd060b934dddc42a88e9ba26591d0590d29dbb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05319. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In LLM-based recommendation, memory acts as a user-level agent in a memory-augmented backbone. Yet users and items remain asymmetric: only the user is given a structured profile; it enters a bandwidth-limited reranker prompt; and it is frozen after warmup. We recast LLM-based recommendation as an agentic-communication process in four stages: BUILD a self-description, TRANSMIT it along the collaborative graph, UNDERSTAND the other side, and SYNC it from the next interaction. This formulation reveals three unresolved communication challenges: the item side never produces a comparable self-description (one-sided BUILD); profile-level signals enter only the bandwidth-limited reranker prompt rather than retrieval, where they would not compete for context tokens (prompt-trapped UNDERSTAND); and the user's description is frozen after warmup with no principled update rule (absent SYNC). We instantiate the missing stages as HARP (Homophily-aware Agentic Recommendation via dual Profiles), a training-free, three-operator addition to a frozen LLM backbone: a rule-extracted symmetric item profile (zero extra LLM calls), a channel-decomposable profile-level homophily H(phi_u, phi_i) consumed at retrieval time rather than inside the reranker prompt, and a single-pass reflective update realising in-context profile evolution without any gradient step. On four public benchmarks (Yelp, Books, MovieTV, Goodreads), HARP lifts Hit@1 over the strongest published baseline by 6.9%-24.0%, with family-wise Holm-corrected p < 1e-9 on every dataset. Ablations and a per-case attribution study show that the operators contribute complementary gains, with the retrieval-side gate as the main source; we also report the trade-off introduced by the reflective pass. We formulate agentic communication and provide a training-free instantiation. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.05319 — 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 2026-11-04T18:32:37.494Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).