WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance
Delegating a web task involves more than asking a question; it requires transferring a policy: what to verify, how to handle uncertainty, which preferences matter, and when to stop. Yet, current live-web agents are evaluated solely on the final answer, ignoring the policy constraints that define the delegation. A plausible final answer can conceal violations of that policy. Our full live audit reveals this critical gap: a strong controller completes 99.2% of tasks but honors all policy constrain
Record details
Published: 7 August 2026
Source: arXiv cs.HC
Category: Research
Topics: Regulation · Agents & autonomy · Transparency
Retrieved: 10 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
arXiv · 6 August 2026
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
arXiv cs.AI · 5 August 2026
FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows
arXiv · 3 August 2026
Governing Agentic AI in FinTech
arXiv · 11 August 2026
Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
arXiv · 12 August 2026
Governing Agentic AI in FinTech
arXiv cs.CY · 13 August 2026
How to cite this record
ethics.ai (7 August 2026), “WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance,” evidence record 17908, https://ethics.ai/record/17908 (originally published by arXiv cs.HC).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.