Pith. sign in

REVIEW 6 cited by

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.13232 v2 pith:ZBMBCTKT submitted 2024-10-17 cs.CL

classification cs.CL
keywords agentsmodelsworldllmsactionscurrentlanguageobservations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the "world model". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claude-3.5-Sonnet, etc.). Then, we present a World-model-augmented (WMA) web agent, which simulates the outcomes of its actions for better decision-making. To overcome the challenges in training LLMs as world models predicting next observations, such as repeated elements across observations and long HTML inputs, we propose a transition-focused observation abstraction, where the prediction objectives are free-form natural language descriptions exclusively highlighting important state differences between time steps. Experiments on WebArena and Mind2Web show that our world models improve agents' policy selection without training and demonstrate our agents' cost- and time-efficiency compared to recent tree-search-based agents.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. WebSynthesis: World-Model-Guided MCTS for Efficient WebUI-Trajectory Synthesis

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A world-model-guided MCTS pipeline synthesizes 4k web navigation trajectories and yields a WebArena Pass@3 success rate of 20.15%, above OS-Genesis (18.66%) and AgentTrek (11.94%).

  2. IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment

    cs.MA 2025-06 conditional novelty 6.0 of 10

    IndoorWorld is a new multi-agent environment that combines physical task solving with social interaction, and its experiments show effects of collaboration, resource competition, and layout on agent behavior.

  3. Quo Vadis, World Modeling?

    cs.CV 2026-08 conditional novelty 5.0 of 10

    An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.

  4. TAPO: Transition-Aware Policy Optimization for LLM Agents

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Interleaving action-conditioned next-observation supervision with group RL on a shared LLM backbone consistently lifts long-horizon agent success over pure policy optimization.

  5. Self-Improvements in Modern Agentic Systems: A Survey

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Self-improving agents are classified by what they update — foundation-model weights or the surrounding scaffold — and by the signal that drives the update, under a single formal operator.

  6. Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance

    cs.AI 2025-08 conditional novelty 5.0 of 10

    A position paper proposing a four-module memory-augmented AR agent framework that uses stored scene graphs of past user experiences to personalize task guidance.

Pith tools