# MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

arXiv: https://arxiv.org/abs/2605.09131 · HTML: https://mlsanity.com/paper/2605.09131/

## Key facts

- Cited by 1 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 12 of its 12 references that are in the map.
- First posted on arXiv 9 May 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [TaskBench: Benchmarking Large Language Models for Task Automation](https://mlsanity.com/paper/2311.18760/) (2023)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.10090/) (2026)
- [MindJourney: Test-Time Scaling with World Models for Spatial Reasoning](https://mlsanity.com/paper/2507.12508/) (2025)
- [RLVR-World: Training World Models with Reinforcement Learning](https://mlsanity.com/paper/2505.13934/) (2025)
- [VRAG: Learning World Models for Interactive Video Generation](https://mlsanity.com/paper/2505.21996/) (2025)
- [From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction](https://mlsanity.com/paper/2510.19654/) (2025)
- [SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search](https://mlsanity.com/paper/2512.23167/) (2025)
- [SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models](https://mlsanity.com/paper/2509.15536/) (2025)
- [World Models as Reference Trajectories for Rapid Motor Adaptation](https://mlsanity.com/paper/2505.15589/) (2025)

## Built on by (most cited first, 1 of 1)

- [Quo Vadis, World Modeling?](https://mlsanity.com/paper/2608.02713/) (2026)

## Abstract (arXiv)

The Model Context Protocol (MCP) has unified the interface between Large Language Models (LLMs) and external tools, yet a fundamental gap remains in how agents conceptualize the environments within which they operate. Current paradigms are bifurcated: Task-level planning often ignores execution-time dynamics, while reactive execution lacks long-horizon foresight. We present MCP-Cosmos, a framework that infuses generative World Models (WM) into the MCP ecosystem to enable predictive task automation. By unifying three disparate technologies, namely MCP, World Model, and Agent, we demonstrate that a "Bring Your Own World Model" (BYOWM) strategy allows agents to simulate state transitions and refine plans in a latent space before execution. We conducted experiments using two strategies, namely ReAct and SPIRAL with 2 planning models and 3 representative world models over 20+ MCP-Bench tasks. We observed improvements in Agent's environment interaction KPI such as tool success rate and tool parameter accuracy. The framework also offers new metrics such as Execution Quality to generate new insights about the effectiveness of world models compared to baseline.