Evaluating World Models with LLM for Decision Making

• URL: http://arxiv.org/abs/2411.08794v1
• Date: Wed, 13 Nov 2024 17:19:32 GMT
• Title: Evaluating World Models with LLM for Decision Making
• Abstract summary: World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the world due to their generalizability. This work proposes a comprehensive evaluation of the world models with LLMs from the decision making perspective.
• Score: 14.029514959117067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the world due to their generalizability. LLMs also serve as the world model for deliberative reasoning in Reasoning via Planning (RAP) and Tree of Thought (ToT). However, the world models are either evaluated as a general world simulator, or as a functional module of the agent, i.e., predicting the transitions to assist the planning. In this work, we propose a comprehensive evaluation of the world models with LLMs from the decision making perspective. Specifically, we leverage the 31 diverse environments from (Wang et al., 2023;2024) and curate the rule-based policy of each environment for the diverse evaluation. Then, we design three main tasks, i.e., policy verification, action proposal, and policy planning, where the world models can be used for decision making solely. Finally, we conduct the comprehensive evaluation of the advanced LLMs, i.e., GPT-4o and GPT-4o-mini, on the environments for the three main tasks under various settings. The key observations include: i) GPT-4o significantly outperforms GPT-4o-mini on the three main tasks, especially for the tasks which require the domain knowledge, ii) the performance of the world model with LLM will be decreased for long-term decision-making tasks, and iii) the combination of different functionalities of the world model will brings additional unstabilities of the performance.

Related papers

• Towards a Belief-Based World Model for LLM Agents [14.419757676852383]
  World models are a promising way to enhance policy performance.<n>During inference, agents currently use world models to simulate the consequences of candidate actions.<n>We argue that simulation alone is an incomplete interface for decision-making under partial observability.
  arXiv  Detail & Related papers  (2026-08-31T22:48:38Z)
• World Action Planner: Generalizable Decision-Making with Action-Conditioned World Models [54.68021681438324]
  We propose World Action Planner, a robot planning system that leverages the reasoning capabilities of Vision-Language Models (VLMs)<n>Our system enables an agent to propose initial action plans and iteratively refine them via optimization and search, reasoning over imagined world model rollouts.<n>We demonstrate that our approach achieves superior performance across compositional tasks, new layouts, and zero-shot generalization scenarios.
  arXiv  Detail & Related papers  (2026-07-30T02:41:52Z)
• Reinforcement World Model Learning for LLM-based Agents [60.65003139516272]
  Reinforcement World Model Learning (RWML) is a self-conditioned method that learns action-supervised world models for LLM-based agents.<n>Our method aligns simulated next states produced by the model with realized next states observed from the environment.<n>We evaluate our method on ALFWorld and $2$ Bench and observe significant gains over the base model, despite being entirely self-supervised.
  arXiv  Detail & Related papers  (2026-02-05T16:30:08Z)
• LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems [5.310303349822993]
  We investigate how Large Language Models (LLM) can act as world models of user preferences through pairwise reasoning over slates.<n>Our results reveal relationships between task performance and properties of the preference function captured by LLMs.
  arXiv  Detail & Related papers  (2025-11-06T16:54:54Z)
• R-WoM: Retrieval-augmented World Model For Computer-use Agents [15.812606459788471]
  Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments.<n>We probe two core capabilities of world models--future state prediction and reward estimation--through three tasks.<n>We propose the Retrieval-augmented World Model (R-WoM), which grounds simulations by incorporating factual, up-to-date knowledge retrieved from external tutorials.
  arXiv  Detail & Related papers  (2025-10-13T19:52:04Z)
• 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)
• PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning [36.051921179063264]
  Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks.<n>Current approaches predominantly rely on supervised fine-tuning, which often leads models to memorize established task completion trajectories.<n>We introduce an adaptive global plan-based agent paradigm AdaPlan, aiming to synergize high-level explicit guidance with execution.
  arXiv  Detail & Related papers  (2025-08-01T06:17:11Z)
• SimuRA: Towards General Goal-Oriented Agent via Simulative Reasoning Architecture with LLM-Based World Model [88.04128601981145]
  We introduce SimuRA, a goal-oriented architecture for generalized agentic reasoning.<n>modelname overcomes the limitations of autoregressive reasoning by introducing a world model for planning via simulation.<n>World-model-based planning, in particular, shows consistent advantage of up to 124% over autoregressive planning.
  arXiv  Detail & Related papers  (2025-07-31T17:57:20Z)
• Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation [54.3628937181904]
  Internal world models (WMs) enable agents to understand the world's state and predict transitions.<n>Recent large Vision-Language Models (VLMs), such as OpenAI o3, GPT-4o and Gemini, exhibit potential as general-purpose WMs.
  arXiv  Detail & Related papers  (2025-06-27T03:24:29Z)
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning [52.36434784963598]
  We introduce WorldPrediction, a video-based benchmark for evaluating world modeling and procedural planning capabilities of different AI models.<n>We show that current frontier models barely achieve 57% accuracy on WorldPrediction-WM and 38% on WorldPrediction-PP whereas humans are able to solve both tasks perfectly.
  arXiv  Detail & Related papers  (2025-06-04T18:22:40Z)
• AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability [84.52205243353761]
  Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment. We investigate ways of simplifying world models that remain agnostic to the AI agent under evaluation.
  arXiv  Detail & Related papers  (2025-04-06T20:35:44Z)
• EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios [53.26658545922884]
  We introduce EgoPlan-Bench2, a benchmark designed to assess the planning capabilities of MLLMs across a wide range of real-world scenarios. We evaluate 21 competitive MLLMs and provide an in-depth analysis of their limitations, revealing that they face significant challenges in real-world planning. Our approach enhances the performance of GPT-4V by 10.24 on EgoPlan-Bench2 without additional training.
  arXiv  Detail & Related papers  (2024-12-05T18:57:23Z)
• PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making [30.46033960436517]
  We propose a framework PIANIST for decomposing the world model into seven intuitive components. We show that our method works well on two different games that challenge the planning and decision making skills of the agent.
  arXiv  Detail & Related papers  (2024-11-24T22:36:34Z)
• On the Modeling Capabilities of Large Language Models for Sequential Decision Making [52.128546842746246]
  Large pretrained models are showing increasingly better performance in reasoning and planning tasks. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly. In environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities.
  arXiv  Detail & Related papers  (2024-10-08T03:12:57Z)
• On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability [59.72892401927283]
  We evaluate the planning capabilities of OpenAI's o1 models across a variety of benchmark tasks. Our results reveal that o1-preview outperforms GPT-4 in adhering to task constraints.
  arXiv  Detail & Related papers  (2024-09-30T03:58:43Z)
• Making Large Language Models into World Models with Precondition and Effect Knowledge [1.8561812622368763]
  We show that Large Language Models (LLMs) can be induced to perform two critical world model functions. We validate that the precondition and effect knowledge generated by our models aligns with human understanding of world dynamics.
  arXiv  Detail & Related papers  (2024-09-18T19:28:04Z)
• Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models [6.860460230412773]
  We propose an LLM-embodied path planning framework for mobile agents. Our proposed multi-layer architecture uses prompted LLMs in the path planning phase and integrates them with the mobile agents' low-level actuators. Our experiments show that this framework can improve LLMs' 2D plane reasoning abilities and complete coverage path planning tasks.
  arXiv  Detail & Related papers  (2024-07-02T12:38:46Z)
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems [59.40480894948944]
  Large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. Under this model, the LLM Planner navigates a partially observable Markov decision process (POMDP) by iteratively generating language-based subgoals via prompting. We prove that the pretrained LLM Planner effectively performs Bayesian aggregated imitation learning (BAIL) through in-context learning.
  arXiv  Detail & Related papers  (2024-05-30T09:42:54Z)
• WorldGPT: Empowering LLM as Multimodal World Model [51.243464216500975]
  We introduce WorldGPT, a generalist world model built upon Multimodal Large Language Model (MLLM) WorldGPT acquires an understanding of world dynamics through analyzing millions of videos across various domains. We conduct evaluations on WorldNet, a multimodal state transition prediction benchmark.
  arXiv  Detail & Related papers  (2024-04-28T14:42:02Z)
• 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)
• Improving Planning with Large Language Models: A Modular Agentic Architecture [7.63815864256878]
  Large language models (LLMs) often struggle with tasks that require multi-step reasoning or goal-directed planning. We propose an agentic architecture, the Modular Agentic Planner (MAP), in which planning is accomplished via the recurrent interaction of specialized modules. We find that MAP yields significant improvements over both standard LLM methods.
  arXiv  Detail & Related papers  (2023-09-30T00:10:14Z)
• AdaPlanner: Adaptive Planning from Feedback with Language Models [56.367020818139665]
  Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback. To mitigate hallucination, we develop a code-style LLM prompt structure that facilitates plan generation across a variety of tasks, environments, and agent capabilities.
  arXiv  Detail & Related papers  (2023-05-26T05:52:27Z)

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.