# WebRider: Persona-Conditioned Intent Controllers for Live-Web Assistance

arXiv: https://arxiv.org/abs/2608.06704 · HTML: https://mlsanity.com/paper/2608.06704/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://mlsanity.com/paper/2402.05930/) (2024)
- [The BrowserGym Ecosystem for Web Agent Research](https://mlsanity.com/paper/2412.05467/) (2024)
- [Multimodal Web Navigation with Instruction-Finetuned Foundation Models](https://mlsanity.com/paper/2305.11854/) (2023)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge](https://mlsanity.com/paper/2506.21506/) (2025)
- [Large Language Models Empowered Personalized Web Agents](https://mlsanity.com/paper/2410.17236/) (2024)
- [RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users](https://mlsanity.com/paper/2504.10445/) (2025)
- [BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks](https://mlsanity.com/paper/2510.02418/) (2025)
- [Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History](https://mlsanity.com/paper/2602.17003/) (2026)
- [World-Model-Augmented Web Agents with Action Correction](https://mlsanity.com/paper/2602.15384/) (2026)
- [Why Do LLM-based Web Agents Fail? A Hierarchical Planning Perspective](https://mlsanity.com/paper/2603.14248/) (2026)
- [Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild](https://mlsanity.com/paper/2603.29020/) (2026)
- [Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts](https://mlsanity.com/paper/2602.02468/) (2026)
- [Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization](https://mlsanity.com/paper/2604.11259/) (2026)
- [PersonaFingerprint: Measuring Persona Inference on Modern Websites with LLM-Driven Browsing](https://mlsanity.com/paper/2605.15962/) (2026)
- [SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents](https://mlsanity.com/paper/2605.14205/) (2026)

## Abstract (arXiv)

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 constraints in only 38.8% of cases. Finishing does not imply fidelity. WebRider bridges this gap by formalizing the delegated policy as an intent contract---an operational record of goals, constraints, evidence obligations, answer form, and task-local persona controls that must hold even as web pages change. WebRider employs a hierarchical architecture: a top-layer controller maintains the contract, a middle layer realizes intentions as guarded executable actions, and a tool layer executes these actions via browser, search, and maps tools. Our benchmark, RiderBench, evaluates this design on 4,096 live-web contracts across 42 public websites, auditing both the internal contract state and the visible user experience to determine if a rollout preserved its policy and if the steps were persona-consistent. The guarded middle interface also serves as a high-quality training signal; an 8B action-policy model trained through this interface outperforms executable-only baselines under a fixed controller. By making the browsing path a first-class object, WebRider enables a system that is auditable, human-judgeable, and learnable without conflating action realization with final-answer decisions. Dataset URL: hf.co/datasets/WebRider/WebRider.