R-WoM: Retrieval-augmented World Model For Computer-use Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908872807022592 |
|---|---|
| author | Mei, Kai Guo, Jiang Chang, Shuaichen Dong, Mingwen Lee, Dongkyu Niu, Xing Jiang, Jiarong |
| author_facet | Mei, Kai Guo, Jiang Chang, Shuaichen Dong, Mingwen Lee, Dongkyu Niu, Xing Jiang, Jiarong |
| contents | Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However, this capability is fundamentally limited by LLMs' tendency toward hallucination and their reliance on static training knowledge, which can lead to compounding errors that inhibit long-horizon simulations. To systematically investigate whether LLMs are appropriate for world modeling, we probe two core capabilities of world models--future state prediction and reward estimation--through three tasks: next-state identification, full-procedure planning alignment, and milestone transition recognition. Our analysis shows that while LLMs effectively capture immediate next states and identify meaningful state transitions, their performance rapidly degrades in full-procedure planning. This highlights LLMs' limitations in reliably modeling environment dynamics over long horizons. To address these limitations, we propose the Retrieval-augmented World Model (R-WoM), which grounds LLM simulations by incorporating factual, up-to-date knowledge retrieved from external tutorials. Experiments show that R-WoM achieves relative improvements of up to 23.4% and 16.3% on the subsets of OSWorld and Webarena compared to baselines, with particular advantage in longer-horizon simulations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | R-WoM: Retrieval-augmented World Model For Computer-use Agents Mei, Kai Guo, Jiang Chang, Shuaichen Dong, Mingwen Lee, Dongkyu Niu, Xing Jiang, Jiarong Computation and Language Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However, this capability is fundamentally limited by LLMs' tendency toward hallucination and their reliance on static training knowledge, which can lead to compounding errors that inhibit long-horizon simulations. To systematically investigate whether LLMs are appropriate for world modeling, we probe two core capabilities of world models--future state prediction and reward estimation--through three tasks: next-state identification, full-procedure planning alignment, and milestone transition recognition. Our analysis shows that while LLMs effectively capture immediate next states and identify meaningful state transitions, their performance rapidly degrades in full-procedure planning. This highlights LLMs' limitations in reliably modeling environment dynamics over long horizons. To address these limitations, we propose the Retrieval-augmented World Model (R-WoM), which grounds LLM simulations by incorporating factual, up-to-date knowledge retrieved from external tutorials. Experiments show that R-WoM achieves relative improvements of up to 23.4% and 16.3% on the subsets of OSWorld and Webarena compared to baselines, with particular advantage in longer-horizon simulations. |
| title | R-WoM: Retrieval-augmented World Model For Computer-use Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.11892 |