Context and Diversity Matter: The Emergence of In-Context Learning in World Models

• URL: http://arxiv.org/abs/2509.22353v1
• Date: Fri, 26 Sep 2025 13:50:32 GMT
• Title: Context and Diversity Matter: The Emergence of In-Context Learning in World Models
• Authors: Fan Wang, Zhiyuan Chen, Yuxuan Zhong, Sunjian Zheng, Pengtao Shao, Bo Yu, Shaoshan Liu, Jianan Wang, Ning Ding, Yang Cao, Yu Kang,
• Abstract summary: We investigate in-context environment learning (ICEL), shifting attention from zero-shot performance to the growth and limits of the world model.<n>Our contributions are three-fold: (1) we formalize in-context learning of a world model and identify two core mechanisms: environment recognition and environment learning; (2) we derive error upper-bounds for both mechanisms that expose how the mechanisms emerge; and (3) we empirically confirm that distinct ICL mechanisms exist in the world model.
• Score: 29.11472920301122
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with novel or rare configurations. We investigate in-context environment learning (ICEL), shifting attention from zero-shot performance to the growth and asymptotic limits of the world model. Our contributions are three-fold: (1) we formalize in-context learning of a world model and identify two core mechanisms: environment recognition and environment learning; (2) we derive error upper-bounds for both mechanisms that expose how the mechanisms emerge; and (3) we empirically confirm that distinct ICL mechanisms exist in the world model, and we further investigate how data distribution and model architecture affect ICL in a manner consistent with theory. These findings demonstrate the potential of self-adapting world models and highlight the key factors behind the emergence of ICEL, most notably the necessity of long context and diverse environments.

Related papers

• The Trinity of Consistency as a Defining Principle for General World Models [106.16462830681452]
  General World Models are capable of learning, simulating, and reasoning about objective physical laws.<n>We propose a principled theoretical framework that defines the essential properties requisite for a General World Model.<n>Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.
  arXiv  Detail & Related papers  (2026-02-26T16:15:55Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction [53.745458605360675]
  We explore world-model internalization through efficient interaction and active reasoning (WMAct)<n>WMAct liberates the model from structured reasoning, allowing the model to shape thinking directly through its doing.<n>Our experiments on Sokoban, Maze, and Taxi show that WMAct yields effective world model reasoning capable of resolving tasks in a single turn.
  arXiv  Detail & Related papers  (2025-11-28T18:59:47Z)
• Social World Model-Augmented Mechanism Design Policy Learning [58.739456918502704]
  We introduce SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically to enhance mechanism design.<n>We show that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.
  arXiv  Detail & Related papers  (2025-10-22T06:01:21Z)
• The Physical Basis of Prediction: World Model Formation in Neural Organoids via an LLM-Generated Curriculum [0.0]
  We present a curriculum of three scalable, closed-loop virtual environments designed to train human neural organoids.<n>We detail the design of three distinct task environments that demand progressively more sophisticated world models for successful decision-making.<n>This work bridges the gap between model-based reinforcement learning and computational neuroscience, offering a unique platform for studying embodiment, decision-making, and the physical basis of intelligence.
  arXiv  Detail & Related papers  (2025-09-04T19:51:00Z)
• Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models [93.1043186636177]
  We explore the hypothesis that people use a combination of distributed and symbolic representations to construct bespoke mental models tailored to novel situations.<n>We propose a computational implementation of this idea -- a Model Synthesis Architecture''<n>We evaluate our MSA as a model of human judgments on a novel reasoning dataset.
  arXiv  Detail & Related papers  (2025-07-16T18:01:03Z)
• Learning Local Causal World Models with State Space Models and Attention [1.5498250598583487]
  We show that a SSM can model the dynamics of a simple environment and learn a causal model at the same time.<n>We pave the way for further experiments that lean into the strength of SSMs and further enhance them with causal awareness.
  arXiv  Detail & Related papers  (2025-05-04T11:57:02Z)
• A Survey of World Models for Autonomous Driving [55.520179689933904]
  Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling.<n>World models offer high-fidelity representations of the driving environment that integrate multi-sensor data, semantic cues, and temporal dynamics.<n>Future research must address key challenges in self-supervised representation learning, multimodal fusion, and advanced simulation.
  arXiv  Detail & Related papers  (2025-01-20T04:00:02Z)
• SPARTAN: A Sparse Transformer Learning Local Causation [63.29645501232935]
  Causal structures play a central role in world models that flexibly adapt to changes in the environment. We present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns local causal structures between entities in a scene. By applying sparsity regularisation on the attention pattern between object-factored tokens, SPARTAN identifies sparse local causal models that accurately predict future object states.
  arXiv  Detail & Related papers  (2024-11-11T11:42:48Z)
• 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)
• Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspective [2.61072980439312]
  Devising formalisms to develop internal world models is a critical research challenge in the domains of artificial intelligence and machine learning.<n>This thesis identifies several limitations with the prevalent use of state space models as internal world models.<n>The structure of models in formalisms facilitates exact probabilistic inference using belief propagation, as well as end-to-end learning via backpropagation through time.<n>These formalisms integrate the concept of uncertainty in world states, thus improving the system's capacity to emulate the nature of the real world and quantify the confidence in its predictions.
  arXiv  Detail & Related papers  (2024-04-24T12:41:04Z)
• Compete and Compose: Learning Independent Mechanisms for Modular World Models [57.94106862271727]
  We present COMET, a modular world model which leverages reusable, independent mechanisms across different environments. COMET is trained on multiple environments with varying dynamics via a two-step process: competition and composition. We show that COMET is able to adapt to new environments with varying numbers of objects with improved sample efficiency compared to more conventional finetuning approaches.
  arXiv  Detail & Related papers  (2024-04-23T15:03:37Z)
• A Theoretical Analysis of Self-Supervised Learning for Vision Transformers [66.08606211686339]
  Masked autoencoders (MAE) and contrastive learning (CL) capture different types of representations.<n>We study the training dynamics of one-layer softmax-based vision transformers (ViTs) on both MAE and CL objectives.
  arXiv  Detail & Related papers  (2024-03-04T17:24:03Z)
• LEADS: Learning Dynamical Systems that Generalize Across Environments [12.024388048406587]
  We propose LEADS, a novel framework that leverages the commonalities and discrepancies among known environments to improve model generalization. We show that this new setting can exploit knowledge extracted from environment-dependent data and improves generalization for both known and novel environments.
  arXiv  Detail & Related papers  (2021-06-08T17:28:19Z)

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.