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

• URL: http://arxiv.org/abs/2605.09131v1
• Date: Sat, 09 May 2026 19:25:56 GMT
• Title: MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
• Abstract summary: We present MCP-Cosmos, a framework that infuses generative World Models (WM) into the MCP ecosystem to enable predictive task automation.<n>We demonstrate that a "Bring Your Own World Model" (BYOWM) strategy allows agents to simulate state transitions and plans refine in a latent space before execution.
• Score: 2.344185522187755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence [54.62791372989525]
  Action models, vision-language--action policies, and world models have advanced this goal.<n>World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences.<n>We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition.
  arXiv  Detail & Related papers  (2026-07-13T15:22:56Z)
• Bridging the Agent-World Gap: Text World Models for LLM-based Agents [83.8237017249529]
  Large language model (LLM)-based agents are increasingly used in interactive textual environments.<n>Many remain largely reactive, mapping observations to actions without an explicit model of how these environments are structured and evolve.<n>This motivates text world models (TWMs): transition models over textual states that, given a state and a candidate action, predict the resulting webpage, terminal output, API response, or user reply.<n>We systematically review text world models for LLM-based agents, organized around a formal framework and the agent lifecycle.
  arXiv  Detail & Related papers  (2026-06-08T04:58:52Z)
• Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks [44.06996146648851]
  We introduce WorldDP, a world model framework designed for multi-stage robotic manipulation.<n>Our hierarchical approach utilizes a high-level world model as a transition function to optimize for feasible subgoals during runtime.<n>We incorporate object-centric representations that decouple environmental entities and enable us to plan sequentially with respect to each.
  arXiv  Detail & Related papers  (2026-06-07T18:39:45Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• EmbodiedBrain: Expanding Performance Boundaries of Task Planning for Embodied Intelligence [17.644658293987955]
  Embodied AI agents are capable of robust spatial perception, effective task planning, and adaptive execution in physical environments.<n>Current large language models (LLMs) and multimodal LLMs (MLLMs) for embodied tasks suffer from key limitations.<n>We propose EmbodiedBrain, a novel vision-language foundation model available in both 7B and 32B parameter sizes.
  arXiv  Detail & Related papers  (2025-10-23T14:05:55Z)
• ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning [77.49815848173613]
  We propose a framework for abstract world models that jointly learns symbolic state representations and causal processes for both endogenous actions and mechanisms.<n>Across five simulated tabletop robotics environments, the learned models enable fast planning that generalizes to held-out tasks with more objects and more complex goals, outperforming a range of baselines.
  arXiv  Detail & Related papers  (2025-09-30T13:44:34Z)
• Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models [0.0]
  A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or learn them end-to-end.<n>We propose and compare two communication strategies for a cooperative task-allocation problem.<n>Our experiments reveal that while emergent communication is viable in simple settings, the engineered, world model-based approach shows superior performance, sample efficiency, and scalability as complexity increases.
  arXiv  Detail & Related papers  (2025-08-04T21:29:07Z)
• Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach [82.27842884709378]
  We propose a framework that prioritizes natural language understanding and structured reasoning to enhance the agent's global understanding of the environment.<n>Our method outperforms previous approaches, particularly achieving a 44.4% relative improvement in task success rate.
  arXiv  Detail & Related papers  (2025-05-22T09:08:47Z)
• EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning [84.6451394629312]
  We introduce EgoPlan-Bench, a benchmark to evaluate the planning abilities of MLLMs in real-world scenarios. We show that EgoPlan-Bench poses significant challenges, highlighting a substantial scope for improvement in MLLMs to achieve human-level task planning. We also present EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench.
  arXiv  Detail & Related papers  (2023-12-11T03:35:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.