# Current Agents Fail to Leverage World Model as Tool for Foresight

arXiv: https://arxiv.org/abs/2601.03905 · HTML: https://mlsanity.com/paper/2601.03905/

## Key facts

- Cited by 17 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 25 of its 38 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence](https://mlsanity.com/paper/2505.23764/) (2025)
- [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025)
- [3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark](https://mlsanity.com/paper/2412.07825/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models](https://mlsanity.com/paper/2412.07755/) (2024)
- [CWM: An Open-Weights LLM for Research on Code Generation with World Models](https://mlsanity.com/paper/2510.02387/) (2025)
- [VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents](https://mlsanity.com/paper/2510.16907/) (2025)
- [An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2411.06048/) (2024)
- [Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation](https://mlsanity.com/paper/2508.19958/) (2025)
- [World-in-World: World Models in a Closed-Loop World](https://mlsanity.com/paper/2510.18135/) (2025)
- [REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites](https://mlsanity.com/paper/2504.11543/) (2025)
- [Pre-Trained Video Generative Models as World Simulators](https://mlsanity.com/paper/2502.07825/) (2025)
- [Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2502.16707/) (2025)
- [Energy-Based Transformers are Scalable Learners and Thinkers](https://mlsanity.com/paper/2507.02092/) (2025)
- [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025)
- [REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks](https://mlsanity.com/paper/2502.18836/) (2025)
- [Can World Models Benefit VLMs for World Dynamics?](https://mlsanity.com/paper/2510.00855/) (2025)
- [MARPLE: A Benchmark for Long-Horizon Inference](https://mlsanity.com/paper/2410.01926/) (2024)

## Built on by (most cited first, 17 of 17)

- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [WebWorld: A Large-Scale World Model for Web Agent Training](https://mlsanity.com/paper/2602.14721/) (2026)
- [Reinforcement World Model Learning for LLM-based Agents](https://mlsanity.com/paper/2602.05842/) (2026)
- [When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning](https://mlsanity.com/paper/2602.08236/) (2026)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [Self-Evolving World Models for LLM Agent Planning](https://mlsanity.com/paper/2606.30639/) (2026)
- [AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints](https://mlsanity.com/paper/2606.05622/) (2026)
- [Aligning Agentic World Models via Knowledgeable Experience Learning](https://mlsanity.com/paper/2601.13247/) (2026)
- [Bridging the Agent-World Gap: Text World Models for LLM-based Agents](https://mlsanity.com/paper/2606.09032/) (2026)
- [CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing](https://mlsanity.com/paper/2605.02910/) (2026)
- [Safety, Security, and Cognitive Risks in World Models](https://mlsanity.com/paper/2604.01346/) (2026)
- [Self-Execution Simulation Improves Coding Models](https://mlsanity.com/paper/2604.03253/) (2026)
- [World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning](https://mlsanity.com/paper/2606.03603/) (2026)
- [Efficient Agentic Reasoning Through Self-Regulated Simulative Planning](https://mlsanity.com/paper/2605.22138/) (2026)
- [Quo Vadis, World Modeling?](https://mlsanity.com/paper/2608.02713/) (2026)
- [PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation](https://mlsanity.com/paper/2610.04916/) (2026)
- [Software World Models: From Consequence Prediction to Decision Value](https://mlsanity.com/paper/2610.04940/) (2026)

## Abstract (arXiv)

Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external simulators to foresee outcomes before acting. This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition. Across diverse agentic and visual question answering tasks, we observe that some agents rarely invoke simulation (fewer than 1%), frequently misuse predicted rollouts (approximately 15%), and often exhibit inconsistent or even degraded performance (up to 5%) when simulation is available or enforced. Attribution analysis further indicates that the primary bottleneck lies in the agents' capacity to decide when to simulate, how to interpret predicted outcomes, and how to integrate foresight into downstream reasoning. These findings underscore the need for mechanisms that foster calibrated, strategic interaction with world models, paving the way toward more reliable anticipatory cognition in future agent systems.