dorsal/arxiv
View SchemaSERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
| Authors | Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tianhua Zhou, Xiaojia Chang, Jingbo Zhu, Tong Xiao |
|---|---|
| Categories | |
| ArXiv ID | 2601.09515vv1 |
| URL | https://arxiv.org/abs/2601.09515 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings with massive query streams, this technique faces two challenges: (1) informative samples are often sparse and difficult to identify, and (2) pseudo-labels generated by the current model could be unreliable. To address these challenges, in this work, we propose a Self-Evolving Relevance Model approach (SERM), which comprises two complementary multi-agent modules: a multi-agent sample miner, designed to detect distributional shifts and identify informative training samples, and a multi-agent relevance annotator, which provides reliable labels through a two-level agreement framework. We evaluate SERM in a large-scale industrial setting, which serves billions of user requests daily. Experimental results demonstrate that SERM can achieve significant performance gains through iterative self-evolution, as validated by extensive offline multilingual evaluations and online testing.
{
"annotation_id": "3c2ca307-721d-4f08-ad7b-837a80229fca",
"date_created": "2026-02-17T05:53:20.401000Z",
"date_modified": "2026-02-17T05:53:20.401000Z",
"file_hash": "2545dce165f1f24b7440d2c0758a6b53eba762e8b0f50e2a18de2cf9a45c7f95",
"private": false,
"record": {
"abstract": "Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings with massive query streams, this technique faces two challenges: (1) informative samples are often sparse and difficult to identify, and (2) pseudo-labels generated by the current model could be unreliable. To address these challenges, in this work, we propose a Self-Evolving Relevance Model approach (SERM), which comprises two complementary multi-agent modules: a multi-agent sample miner, designed to detect distributional shifts and identify informative training samples, and a multi-agent relevance annotator, which provides reliable labels through a two-level agreement framework. We evaluate SERM in a large-scale industrial setting, which serves billions of user requests daily. Experimental results demonstrate that SERM can achieve significant performance gains through iterative self-evolution, as validated by extensive offline multilingual evaluations and online testing.",
"arxiv_id": "2601.09515",
"authors": [
"Chenglong Wang",
"Canjia Li",
"Xingzhao Zhu",
"Yifu Huo",
"Huiyu Wang",
"Weixiong Lin",
"Yun Yang",
"Qiaozhi He",
"Tianhua Zhou",
"Xiaojia Chang",
"Jingbo Zhu",
"Tong Xiao"
],
"categories": [
"cs.CL"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams",
"url": "https://arxiv.org/abs/2601.09515",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "b372a93d-fbc5-44b5-8b4a-f906f3d5d4e6",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}