---
title: 'Agent-World: World Models & Simulation'
url: https://www.emergentmind.com/topics/agent-world
type: topic
---

# Agent-World: World Models & Simulation

Agent-World denotes a line of research in which autonomous behavior depends on an explicit world representation or world substrate that mediates between observation, action, and learning. In recent work, that world may be an internal cognitive map built from DOM trees and semantic service descriptions, a text or language world model that predicts next observations, a fully synthetic executable environment for tool-using reinforcement learning, a shared semantic world for multi-agent systems, or a multi-view generative model that keeps multiple agents synchronized to one underlying scene [2510.24459][2606.09032][2602.10090][2604.01359][2603.02697]. This suggests that Agent-World is not a single architecture but a family of approaches organized around how agents construct, simulate, share, and update the worlds in which they operate.

## 1. Conceptual scope and definitions

The literature uses the term in several precise senses. In one strand, the “world” is an internal actionable representation, such as a cognitive map or world model that fuses perceptual streams into a task-usable structure. In another, the “world” is an executable environment whose state, actions, observations, and rewards are explicitly specified. In a third, the “world” is a shared semantic substrate that multiple agents inhabit and modify. In a fourth, the “world” is a synchronized generative process that must remain consistent across multiple agents and viewpoints.

| Sense of Agent-World | Canonical object | Representative sources |
|---|---|---|
| Internal actionable representation | cognitive map / world model, Page Affordance Model, affordance catalog | [2510.24459] |
| Executable training world | POMDP with database state and tool-mediated actions | [2602.10090][2604.18292] |
| Shared explicit world | world-centered multi-agent system $W=(E,R,S,A,T,C)$ | [2604.01359] |
| Shared generative world | synchronized multi-agent videos or multi-view latent world state | [2603.02697][2604.18564][2605.28816] |
| Language world model | next-observation predictor or text world model | [2606.24597][2606.09032] |

A recurring misconception is that a world model must always be a latent dynamics module in the model-based RL sense. The current literature is broader. It includes explicit semantic ontologies, hierarchical task graphs, executable simulators, symbolic domains, and text-rendered transition models, in addition to learned latent predictors [2604.01359][2509.04731][2512.22336].

## 2. World construction from structured digital environments

A central Agent-World formulation treats web and service interaction as a world-model construction problem rather than direct action on raw structure. In this formulation, raw HTML and API descriptions are not yet agent-usable worlds. Raw DOM is highly verbose, contains scripts, styles, trackers, and boilerplate, and cited pruning studies suggest that **80–90%** may be non-semantic; hardcoded API integrations are brittle because they couple the agent to a particular service version, break under change, and prevent runtime discovery [2510.24459].

The proposed remedy is a pattern language with two complementary architectural patterns. The **DOM Transduction Pattern** inserts a **DOM Transformer** into perception. It ingests a structured DOM tree and outputs a **Page Affordance Model (PAM)** through cleaning, pruning, compact representation, and optionally an **LLM-as-Transformer** stage. The explicit requirement is that PAM preserve the essential structure of task-relevant interactive elements while remaining decoupled from the reasoning core. The **Hypermedia Affordances Recognition Pattern** addresses unknown services and devices by parsing standardized semantic descriptions, most concretely **W3C Web of Things Thing Description (TD)**, extracting **Properties**, **Actions**, **Events**, and protocol bindings, and updating the cognitive map with an affordance catalog discovered at runtime [2510.24459].

This view aligns closely with the formalization of **text world models (TWMs)**, where a transition model predicts the next textual state from the current state and action,
$$
M : \mathcal{S} \times \mathcal{A} \to \mathcal{T}_{\mathcal{S}}, \qquad \hat{s}_{t+1}=M(s_t,a_t),
$$
and the successor state may be natural language, JSON, key-value records, accessibility trees, PDDL-style predicates, or executable code [2606.09032]. The survey literature further organizes construction methods into **LLM-as-world-model** and **code-as-world-model** paradigms, separating implicit dynamics absorbed into weights from executable dynamics externalized into programs [2606.09032].

The significance of this strand is representational rather than merely compressive. The objective is not just to shorten input, but to convert external structure into affordance-bearing internal state. This suggests that, in digital environments, much of the Agent-World problem is a problem of choosing the right intermediate world representation rather than a problem of direct end-to-end action selection.

## 3. Synthetic, executable, and self-evolving environments

Another major use of Agent-World concerns the construction of executable training worlds. **Agent World Model (AWM)** defines each synthetic environment as a POMDP,
$$
E_i = (\mathcal{S}_{E_i}, \mathcal{A}_{E_i}, \mathcal{O}_{E_i}, T_{E_i}, \{R_\tau\}_{\tau \in \mathcal{T}_{E_i}}),
$$
with the design principle **database = state**, **MCP tool interface = action/observation layer**, and **verification code = reward construction** [2602.10090]. The pipeline scales to **1,000 environments** and **10,000 tasks**, backed by **35,062 tools** total, with an average of **35.1 exposed tools per environment**, **18.5 database tables**, **129.3 sample data records**, **8.5 agent steps per task**, and **7.1 unique tools used per task**; **13.7% of tasks exceeded the 20-step budget** during complexity analysis [2602.10090]. The stated motivation is that code-driven, database-backed environments provide more reliable transitions and cheaper repeated interaction than LLM-simulated environments.

A complementary line scales realistic rather than purely synthetic environments. **Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence** introduces two components: **Agentic Environment-Task Discovery** and **Continuous Self-Evolving Agent Training** [2604.18292]. The environment ecosystem contains **1,978 retained environments** and **19,822 distinct tools** from over **2K themes**, and training is evaluated on **23 benchmarks**. The paper reports that increasing the number of training environments from 0 to approximately 2000 raises the average across four representative domains from **18.4%** to **38.5%**, and that self-evolution rounds yield monotonic gains with diminishing returns [2604.18292].

A third executable strand focuses not on environment supply for RL, but on generating world models themselves. **Agent2World** maps a text description $x$ to an executable symbolic world model
$$
F(x)=WM,\qquad WM=(P_{\text{env}},A_{\text{env}},T_{\text{env}}),
$$
with target formats including PDDL and Python [2512.22336]. Its three-stage system comprises **Deep Researcher**, **Model Developer**, and a **Testing Team** that combines adaptive unit testing and simulation-based validation. Only repair trajectories whose final artifacts pass verification are kept for supervised fine-tuning, and the paper reports an **average relative gain of 30.95%** over the same model before training [2512.22336].

These systems treat the world not as a fixed benchmark but as an engineered object: synthesizable, verifiable, and revisable. A plausible implication is that environment quality becomes a first-class scaling axis for general agents, alongside model size and policy optimization.

## 4. Planning, foresight, and language world models

In planning-oriented work, Agent-World refers to predictive machinery that provides foresight before an action is executed. **Agent Planning with World Knowledge Model** formulates interactive planning as a POMDP and distinguishes **prior task knowledge** from **dynamic state knowledge** [2405.14205]. The **World Knowledge Model (WKM)** is a parametric knowledge model trained to self-synthesize knowledge from expert and sampled trajectories, then provide global prior knowledge for early planning and dynamic state knowledge for local planning. The paper reports that WKM reduces blind trial-and-error and hallucinated actions; on ALFWorld, invalid-action rates fall to **32.86%** seen and **29.85%** unseen, compared with higher rates for several baselines [2405.14205].

**WorldEvolver** studies a more explicit foresight setting in which an LLM agent operates in a partially observed interaction process $(\mathcal{S},\mathcal{A},\mathcal{O},\mathcal{T})$, sees
$$
s_t=(o_1,a_1,\ldots,o_{t-1},a_{t-1},o_t),
$$
samples $a_t\sim\pi_\theta(\cdot\mid s_t)$, and queries a frozen world model for predicted future observations [2606.30639]. Its central claim is that foresight helps only when reliable. The framework therefore maintains a memory state
$$
M_t=(M_E^t,M_S^t),
$$
with **Episodic Memory** over realized transitions, **Semantic Memory** over mismatch-derived heuristic rules, and **Selective Foresight** that abstains when confidence is too low. In the reported planning results, Gemma-4-26B-A4B with ReAct improves from **23.88** to **26.12** on ALFWorld and from **44.44** to **52.22** on ScienceWorld when WorldEvolver with selective foresight is used [2606.30639].

At foundation-model scale, **Qwen-AgentWorld** trains native language world models to predict next observations directly from long interaction histories,
$$
\hat{o}_{t+1}=f_\theta(c,o_{\le t},a_{\le t}),
$$
across **7 domains**: MCP, Search, Terminal, SWE, Android, Web, and OS [2606.24597]. Training uses a three-stage recipe summarized as **“CPT injects, SFT activates, RL sharpens”**, built on **more than 10M environment interaction trajectories** and evaluated on **AgentWorldBench**, which contains **2,170 evaluation samples** from **9 established benchmarks** [2606.24597]. On the main five-dimensional rubric average, **Qwen-AgentWorld-397B-A17B** reaches **58.71** overall and **Qwen-AgentWorld-35B-A3B** reaches **56.39**, with the larger model outperforming existing frontier models overall and showing particular strength on Terminal and SWE [2606.24597].

The broader survey literature frames these developments as a response to the **agent-world gap**: many LLM agents remain reactive, whereas world models provide planning, verification, training-time experience synthesis, and principled evaluation [2606.09032]. The literature also stresses that high prediction accuracy does not necessarily imply high task utility, because a next-state predictor may miss the decision-critical information needed by the downstream agent [2606.09032].

## 5. Explicit shared worlds, semantic models, and theoretical necessity

A more explicit and institution-oriented formulation appears in **world-centered multi-agent systems (WMAS)**. Here the primary representational substrate is not each agent’s private belief state, but a shared world
$$
W=(E,R,S,A,T,C),
$$
where $E$ is a set of entities, $R$ a set of relations, $S$ a state space over $(E,R)$, $A$ admissible actions, $T:S\times A\rightarrow S$ a transition function or relation, and $C$ a set of constraints or norms [2604.01359]. WMAS is motivated by structured domains such as enterprises, finance, healthcare organizations, and institutional workflows, where explicit state control, semantic consistency, explainability, long-term stability, and verifiable behavior are required. Its semantic model has a **ground semantic layer** implemented as object ontologies and a **causal knowledge layer** updated by **Semantic Machine Learning (SML)**; **Ontobox** is presented as a concrete realization [2604.01359].

In long-horizon multi-agent learning, explicit world structure is instead cast as a hierarchy of tasks and subgoals. **Language-Driven Hierarchical Task Structures as Explicit World Models for Multi-Agent Learning** argues that failure in robotic soccer arises because environments are too structurally flat, not because they are too low-fidelity [2509.04731]. The proposed world model is a task graph, often a **directed acyclic graph (DAG)**, in which tasks, sub-tasks, dependencies, and intrinsic rewards are first-class objects. The paper introduces benchmark-style metrics including **Compositional Generalization Score (CGS)**, **Curriculum Efficiency Gain (CEG)** with
$$
CEG = T_{baseline}/T_{scaffolded},
$$
and **Scaffolding Brittleness Index (SBI)** [2509.04731]. In this view, the environment becomes an active teacher.

Theoretical work strengthens the claim that world-model-like structure is not optional for competent agency. **General Agents Contain World Models, even under Partial Observability and Stochasticity** proves that sufficiently general, almost optimal agents encode enough information about their environments to permit approximate reconstruction of transition probabilities by black-box querying, even for stochastic agents in partially observable environments [2602.03146]. The result is behavioral rather than representational: it does not require an explicit symbolic model, but it does imply that competent generalized behavior contains recoverable world information. This suggests a bridge between explicit-world and implicit-world accounts: some Agent-World systems externalize the world, while others necessarily internalize it.

## 6. Embodied, visual, and multi-agent shared-world simulation

In visual and embodied settings, Agent-World often denotes a requirement that multiple observations correspond to one coherent underlying scene. **ShareVerse** introduces **multi-agent shared world modeling** for video generation, using a CARLA-based dataset with **two synchronized agents**, each equipped with **four synchronized cameras**—front, rear, left, and right—yielding **8 video streams total** per sample [2603.02697]. The framework spatially concatenates four views per agent and adds **cross-agent attention blocks** to a pretrained CogVideoX backbone so that spatial-temporal information transfers across agents. It supports **49-frame** generation and reports **PSNR 20.76**, **SSIM 0.6656**, and **LPIPS 0.2791** [2603.02697].

**MultiWorld** generalizes this setting to scalable multi-agent multi-view world modeling through a **Multi-Agent Condition Module (MACM)** and a **Global State Encoder (GSE)** [2604.18564]. MACM provides identity-aware, interaction-aware conditioning over multiple agent actions, while GSE uses a pretrained **VGGT** backbone to encode a shared 3D-aware latent state from multiple views. On the reported multi-player game dataset, MultiWorld achieves **FVD 179**, **Action 89.8**, and **RPE 0.67**, outperforming several baselines on overall fidelity and multi-view consistency; on multi-robot manipulation it attains **FVD 96** and **RPE 1.52** [2604.18564]. **Gamma-World** extends multi-agent world modeling beyond two players through **Simplex Rotary Agent Encoding**, **Sparse Hub Attention**, and a teacher-student pipeline enabling rollout at **24 FPS**, with the reported ability to generalize from two to four players without additional training [2605.28816].

For model-based MARL, the shared world need not be pixel-based. **DIMA** models global state transitions in cooperative Dec-POMDPs through sequential revelation of agent actions, aligning uncertainty reduction with a diffusion-inspired reverse process over the next state [2505.20922]. It reports state-of-the-art performance on MAMuJoCo and Bi-DexHands, for example **4881 ± 756** on Ant-2x4 and **259.9 ± 4.1** on BottleCap [2505.20922]. **MATWM** instead uses a transformer-based world model with decentralized imagination, a semi-centralized critic, and a teammate prediction module, and reports strong sample efficiency, including near-optimal performance in as few as **50K environment interactions** [2506.18537].

Embodied simulation platforms expand the notion further. **AgentWorld** is an interactive simulation platform for household mobile manipulation that combines automated scene construction, VR-based teleoperation, imitation-learning data collection, and sim-to-real transfer [2508.07770]. It supports multiple embodiments including **Unitree G1**, **Unitree H1**, **Franka Emika Panda**, **DOBOT X-Trainer**, and **TRX-Hand5**, uses RGB observations at **480 × 640**, and defines hybrid mobile-manipulation state and action spaces over arm, end-effector, floating base, and a binary locomotion/manipulation mode selector [2508.07770]. **SimWorlds** addresses dynamic 4D scene creation in Blender through a planner-coder-reviewer workflow, a fixed ordered stage sequence, a layered scene protocol, and deterministic verification. Its **4DBuildBench** contains **50 scenes**—**45 dynamic** and **5 static**—and SimWorlds reports **MPR 0.87**, **SPR 0.89**, and **VLM score 0.82**, outperforming VIGA on mechanism and structural correctness [2607.01766].

A different embodied multi-agent perspective appears in **Multi-Agent Craftax (MAC)**, an efficient open-world environment for social learning. MAC runs **100 million training steps in under one hour on a single GPU**, uses **4 agents** in the reported experiments, and studies whether agents learn from experts, tool sharing, cooperation, or competition [2508.15679]. The salient negative result is that social learning from experts did not improve performance meaningfully: the cultural transmission score is reported as **$-0.056 \pm 0.083$** without auxiliary loss and **$-0.010 \pm 0.080$** with auxiliary loss [2508.15679]. This result complicates simple claims that richer worlds automatically yield richer learning.

## 7. Evaluation, limitations, and open problems

Evaluation in Agent-World research is heterogeneous because the “world” itself varies. The survey on text world models separates evaluation of the world model from evaluation using the world model as an environment, and notes that metrics such as exact match, token F1, consistency ratio, and behavior-consistency variants may disagree with downstream planning value [2606.09032]. This is echoed in system-specific studies. **WorldEvolver** reports that noisy foresight can hurt planning more than no foresight at all [2606.30639]. **SimWorlds** explicitly separates **engine-state audit** from itemized VLM judging because vision models are unreliable at detecting whether motion was produced by the correct physical mechanism [2607.01766]. **Agent2World** argues that parseability and static validation are insufficient because behavior-level failures appear only during interactive execution [2512.22336].

The limitations are similarly varied. In the DOM/service setting, aggressive pruning can remove critical elements, and dynamic service discovery depends on correctly published Thing Descriptions [2510.24459]. In language world modeling, GUI domains remain weaker under text-centric simulation, and factuality is the lowest-scoring rubric dimension even after RL in Qwen-AgentWorld [2606.24597]. In multi-agent video generation, ShareVerse is limited to **two agents** and remains simulation-based, while a **real-time, long-term consistent shared world model** is still described as an open direction [2603.02697]. MultiWorld notes that large-scale training remains unexplored due to computational constraints and that small or distant agents can remain ambiguous because of limited spatial resolution [2604.18564]. In social-learning worlds, MAC shows that current social-learning mechanisms do not yet reliably exploit expert presence or proximity [2508.15679].

Several open problems recur across strands. One is **world model–policy coupling**: whether the world model should be shared with the agent, decoupled as a simulator, or used only as a verifier or critic [2606.09032]. Another is **adaptation under drift**: websites change, APIs evolve, user behavior shifts, and world models must update without catastrophic forgetting or uncontrolled simulator drift [2606.30639][2606.24597]. A third is **mechanism fidelity**: many tasks require not merely plausible outputs but correct state transitions, causal structure, or physically valid construction [2512.22336][2607.01766]. A fourth is **world scale**: several papers report positive scaling with environment diversity, self-evolution rounds, or numbers of agents and views, but also identify diminishing returns and growing systems complexity [2604.18292][2605.28816].

Taken together, these works suggest a common thesis. Agent capability is increasingly being treated not as policy competence alone, but as the joint ability to build, query, inhabit, and revise a world. Whether the world is internal, executable, shared, semantic, symbolic, or generative, the contemporary Agent-World literature treats world construction and world maintenance as core problems of autonomous intelligence rather than auxiliary implementation details.

Source: https://www.emergentmind.com/topics/agent-world