Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Weihao, He, Keqing, Kuang, Chuqiao, Li, Xiaoguang, He, Junxian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912633560498176
author Zeng, Weihao
He, Keqing
Kuang, Chuqiao
Li, Xiaoguang
He, Junxian
author_facet Zeng, Weihao
He, Keqing
Kuang, Chuqiao
Li, Xiaoguang
He, Junxian
contents Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and selecting among multiple candidate outputs. Combining these two strategies has led to the most powerful AI systems, such as Grok 4 Heavy and GPT-5 Pro. In certain contexts (e.g., solving Sudoku puzzles), verifying responses can be substantially easier than generating them. This property, referred to as \emph{asymmetric verification}, highlights the strong potential of test-time scaling (TTS). In this work, we study both sequential and parallel TTS of deep search agents, motivated by the intuition that verification in this setting is often much easier than generation. In experiments, we first show that sequential scaling methods, such as budget forcing, can be effective initially but soon degrade performance. Leveraging asymmetric verification, however, we are able to achieve substantial improvements by allocating only a modest amount of compute to the verifier. We conduct experiments with flagship open-source models and extend them to their ``Heavy'' variants through TTS. These deep research agents achieve gains of up to 27 absolute points on benchmarks such as BrowseComp. Remarkably, as an open-source alternative, GLM-4.5 Heavy reaches accuracy of {\bf 54.0\%} on BrowseComp and {\bf 66.0\%} on GAIA, placing it comparable to the best proprietary choices such as OpenAI Deep Research. Tongyi-DeepResearch Heavy further achieves {\bf 69.0\%} accuracy on BrowseComp, greatly surpassing the best proprietary results.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
Zeng, Weihao
He, Keqing
Kuang, Chuqiao
Li, Xiaoguang
He, Junxian
Artificial Intelligence
Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and selecting among multiple candidate outputs. Combining these two strategies has led to the most powerful AI systems, such as Grok 4 Heavy and GPT-5 Pro. In certain contexts (e.g., solving Sudoku puzzles), verifying responses can be substantially easier than generating them. This property, referred to as \emph{asymmetric verification}, highlights the strong potential of test-time scaling (TTS). In this work, we study both sequential and parallel TTS of deep search agents, motivated by the intuition that verification in this setting is often much easier than generation. In experiments, we first show that sequential scaling methods, such as budget forcing, can be effective initially but soon degrade performance. Leveraging asymmetric verification, however, we are able to achieve substantial improvements by allocating only a modest amount of compute to the verifier. We conduct experiments with flagship open-source models and extend them to their ``Heavy'' variants through TTS. These deep research agents achieve gains of up to 27 absolute points on benchmarks such as BrowseComp. Remarkably, as an open-source alternative, GLM-4.5 Heavy reaches accuracy of {\bf 54.0\%} on BrowseComp and {\bf 66.0\%} on GAIA, placing it comparable to the best proprietary choices such as OpenAI Deep Research. Tongyi-DeepResearch Heavy further achieves {\bf 69.0\%} accuracy on BrowseComp, greatly surpassing the best proprietary results.
title Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
topic Artificial Intelligence
url https://arxiv.org/abs/2510.06135