SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.24422 · 2026

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

Yang Zhao, Han Li, Kun Gai, Tong Zhao, Xiao Liang, Chenyi Lei, Wenwu Ou, Xinyu Sun, Ying Yang, Siyuan Wang, Jing Chen, Zihan Liang, and 11 more

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2603.24422.json · badge: /api/ran/2603.24422.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
benchen4395/onesearch-family canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
composite_item_reward_func Ran
ran, honoured the contract we drafted
benchen4395/onesearch-family/rlhf/train_grpo.py
pointer only (licence: NONE) · get_code("f1628ae626696c59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

concatenated_inputs Ran
ran; our contract draft was wrong, not the code
benchen4395/onesearch-family/rlhf/listwisedpo.py
pointer only (licence: NONE) · get_code("7e7af3c25d8c53fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

concatenated_inputs_sdpo Ran
ran; our contract draft was wrong, not the code
benchen4395/onesearch-family/rlhf/listwisedpo.py
pointer only (licence: NONE) · get_code("7e4675a4df245900")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

l2_normalize Ran
ran, violated the contract we drafted
benchen4395/onesearch-family/rq-opq/keyword_enhance.py
pointer only (licence: NONE) · get_code("376fa049b3508a72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

merger_query_item Ran
ran, honoured the contract we drafted
benchen4395/onesearch-family/rq-opq/rq_dynamic.py
pointer only (licence: NONE) · get_code("de3af5a1e53bffd1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_to_length Ran
ran; our contract draft was wrong, not the code
benchen4395/onesearch-family/rlhf/listwisedpo.py
pointer only (licence: NONE) · get_code("21ba0273539ebdcc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, benchen4395/onesearch-family when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits. However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement. To address these challenges, we propose OneSearch-V2, a latent reasoning enhanced self-distillation generative search framework. It contains three key innovations: (1) a thought-augmented complex query understanding module, which enables deep query understanding and overcomes the shallow semantic matching limitations of direct inference; (2) a reasoning-internalized self-distillation training pipeline, which uncovers users' potential yet precise e-commerce intentions beyond log-fitting through implicit in-context learning; (3) a behavior preference alignment optimization system, which mitigates reward hacking arising from the single conversion metric, and addresses personal preference via direct user feedback. Extensive offline evaluations demonstrate OneSearch-V2's strong query recognition and user profiling capabilities. Online A/B tests further validate its business effectiveness, yielding +3.98% item CTR, +2.07% buyer volume, and +2.11% order volume. Manual evaluation further confirms gains in search experience quality, with +1.37% in page good rate and +1.65% in query-item relevance. More importantly, OneSearch-V2 effectively mitigates common search system issues such as information bubbles and long-tail sparsity, without incurring additional inference costs or serving latency. Key codes are available at https://github.com/benchen4395/onesearch-family.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.24422")
get_code_for_paper("2603.24422")
have("2603.24422")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.24422.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.24422.svg)](https://syntology.ai/paper/2603.24422)

Connect an agent — have() is free.