arXiv cs.AI· Jinming Nian, Jyun-Yu Jiang, Henry Tsai, Yi Fang, Zhirong Liang·· 12 小时前AI 评分31
用 LLM 驱动的进化搜索优化生成式检索的语义索引
Evolving Semantic Indexes for Generative Retrieval
AI 导读
研究者提出用 LLM 驱动的进化程序搜索改进生成式检索（GR）的语义标识符（SID）设计，据称是该方法首次应用于 GR。本地部署的开源 31B 模型负责变异可执行的 GR 组件，1M 参数代理解码器替代反复训练 1B 目标生成器提供快速反馈，在 NQ320K 上代理与目标的 Recall@100 秩相关达 Spearman ρ=0.90。
正文 · 原文
Abstract:Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely determines GR quality, but its discrete, interdependent components (SID construction, collision handling, decoding, and training) cannot be optimized end-to-end with gradients and remain largely hand-designed. We introduce a framework that improves these components through LLM-driven evolutionary program search, to our knowledge the first application of this approach to GR. A locally served, open-weight 31B model mutates executable GR components, so no proprietary LLM API is used, and a 1M-parameter proxy decoder provides fast feedback in place of repeatedly training the 1B target generator. Across 21 SID programs on NQ320K, proxy and target Recall@100 show strong rank correlation (Spearman $\rho = 0.90$). Guided by this proxy, evolution improves the seed GR on NQ320K, MSMARCO300K, and a multilingual e-commerce dataset under a fixed training recipe. On NQ320K, jointly evolving SID construction and collision handling improves Recall@1 from 55.8% to 59.3% and Recall@100 from 85.8% to 90.6%. A component study shows that proxy reliability depends on what is evolved: improvements transfer reliably for the semantic index but not for the generator's training objective or the full pipeline. LLM-driven evolutionary search is thus a practical tool for GR design, provided proxy reliability is established for the chosen search space.
| Subjects: | Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.28568 [cs.AI] |
| (or arXiv:2610.28568v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28568 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jinming Nian [view email]
[v1]
Tue, 20 Oct 2026 17:27:46 UTC (234 KB)
来源：arXiv cs.AI · arxiv.org