Agentic Test-Time Scaling for WebAgents

[2602.12276] Agentic Test-Time Scaling for WebAgents Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2602.12276 (cs) [Submitted on 12 Feb 2026 ( v1 ), last revised 14 Aug 2026 (this version, v2)] Title: Agentic Test-Time Scaling for WebAgents Authors: Nicholas Lee , Lutfi Eren Erdogan , Chris Joseph John , Surya Krishnapillai , Michael W. Mahoney , Kurt Keutzer , Amir Gholami View a PDF of the paper titled Agentic Test-Time Scaling for WebAgents, by Nicholas Lee and 6 other authors View PDF HTML (experimental) Abstract: Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long horizons; and we find that naive policies that uniformly increase sampling show diminishing returns. In this work, we present CATTS, a simple technique for dynamically allocating compute for multi-step agents. We first conduct an empirical study of inference-time scaling for web agents. We find that uniformly increasing per-step compute quickly saturates in long-horizon environments. We then investigate stronger aggregation strategies, including an LLM-based Arbiter that can outperform naive voting, but that can overrule high-consensus decisions. We show that uncertainty statistics derived from the agent's own vote distribution (entropy and top-1/top-2 margin) correlate with downstream success and provide a practical signal for dynamic compute allocation. Based on these findings, we introduce Confidence-Aware Test-Time Scaling (CATTS), which uses vote-derived uncertainty to allocate compute only when decisions are genuinely contentious. CATTS improves performance on WebArena-Lite, Online-Mind2Web, and GoBrowse by up to 11.8% over majority voting while using fewer tokens than uniform scaling, providing both efficiency gains and an interpretable decision rule. Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL) Cite as: arXiv:2602.12276 [cs.AI] (or arXiv:2602.12276v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2602.12276 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Nicholas Lee [ view email ] [v1] Thu, 12 Feb 2026 18:58:30 UTC (765 KB) [v2] Fri, 14 Aug 2026 21:25:10 UTC (539 KB) Full-text links: Access Paper: View a PDF of the paper titled Agentic Test-Time Scaling for WebAgents, by Nicholas Lee and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-02 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents#482214
• IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test Migration#307075
• Framework and Benchmark for Code-Driven Agentic Testing in Web Development#819558
• Framework and Benchmark for Code-Driven Agentic Testing in Web Development#809562
• Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads#405626