---
title: "HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05319v1"
permalink: "https://feed.astralor.com/items/itm_547e2c40d97459454dc16aec"
published: "2026-11-03T18:24:20.000Z"
score: 62
channel: "tech"
tags: ["LLM","AI Agent","RAG","HARP","Training-Free Dual-Profile Agentic","Communication","LLM-Based Recommendation","LLM-based"]
---

# HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation

## 速览

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 p…

## 关键点

- 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 interactio…

## 全文

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 https://github.com/Jove-Zhen/HARP.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_547e2c40d97459454dc16aec