Discriminative World Models for Web Agents

arXiv:2609.02885 · cs.AI, cs.LG · Submitted 2026-09-02 · Read on arXiv

cs.AI, cs.LG

Submitted: 2026-09-02

Updated: 2026-09-02

Project page: https://dhruvpendharkar.github.io/dwm

Terminology

• World Model — 64× in this paper · explained in 7 episodes
• Accuracy — 19× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Process Reward Model — 4× in this paper
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Process Reward Model (PRM) — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
• Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
• Go-Browse: Training Web Agents with Structured Exploration
• The Llama 3 Herd of Models
• Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
• WebCanvas: Benchmarking Web Agents in Online Environments
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration
• WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
• GPT-4o System Card
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Qwen2.5 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
• WebWorld: A Large-Scale World Model for Web Agent Training
• An Illusion of Progress? Assessing the Current State of Web Agents
• Qwen3 Technical Report
• WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents
• GPT-4V(ision) is a Generalist Web Agent, if Grounded

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection