HARP：无需训练的双侧画像智能体通信框架提升 LLM 推荐效果
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
给做 LLM 推荐的朋友：HARP 不训练就能在四个基准上把 Hit@1 拉高 6.9%-24%，物品画像和检索侧门控的思路可以直接借鉴，代码开源了。
论文 HARP 将 LLM 推荐重构为 BUILD、TRANSMIT、UNDERSTAND、SYNC 四阶段智能体通信过程，解决物品侧缺少画像、画像信号只进重排 prompt、用户画像缺少更新规则三个问题。方法在冻结 LLM 骨干上增加三个算子：规则抽取的对称物品画像（零额外 LLM 调用）、在检索阶段消费的画像级同质性度量、以及无需梯度更新的单次反思式画像更新。在 Yelp、Books、MovieTV、Goodreads 四个公开基准上，HARP 将 Hit@1 比最强已发表基线提升 6.9%-24.0%，每个数据集的 family-wise Holm 校正 p < 1e-9。归因分析显示检索侧门控是主要增益来源，代码已在 GitHub 开源。
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
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.