# Discriminative World Models for Web Agents

arXiv: https://arxiv.org/abs/2609.02885 · HTML: https://mlsanity.com/paper/2609.02885/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 2 Sep 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://mlsanity.com/paper/2402.05930/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [Web-Shepherd: Advancing PRMs for Reinforcing Web Agents](https://mlsanity.com/paper/2505.15277/) (2025)
- [Go-Browse: Training Web Agents with Structured Exploration](https://mlsanity.com/paper/2506.03533/) (2025)
- [WebWorld: A Large-Scale World Model for Web Agent Training](https://mlsanity.com/paper/2602.14721/) (2026)
- [MolmoWeb: Open Visual Web Agent and Open Data for the Open Web](https://mlsanity.com/paper/2604.08516/) (2026)
- [WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents](https://mlsanity.com/paper/2601.21872/) (2026)

## Built on by (most cited first, 2 of 2)

- [Agent-Editing World Model: Rethinking World Modeling for LLM Agents](https://mlsanity.com/paper/2609.28416/) (2026)
- [When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models](https://mlsanity.com/paper/2610.05550/) (2026)

## Abstract (arXiv)

Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed representations like HTML or AXTree snapshots. However, this objective is misaligned with the downstream ranker, which relies on predicted states being discriminative across candidates to accurately score them. To address this, we introduce predicted-state matching, a training objective where the predicted representation must distinguish the true resulting state from those reached by alternative actions. We train these models using a branching web-agent dataset derived from WebArena Go-Browse trajectories, where every decision point contains multiple alternative actions and their resulting states. Experiments on our held-out predicted-state matching benchmark show that our approach outperforms world models trained with supervised next-state prediction. We further show that our approach improves PRM-style action ranking on WebPRMBench compared with action-only PRMs and PRMs augmented with supervised-next-state world models. Finally, on WebArena-Lite, using our world model for test-time action selection improves end-to-end task success. Our project page is available at: https://dhruvpendharkar.github.io/dwm/.