From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Hugging Face Daily Papers Papers

Summary

论文提出 Trace2Env,一个免学习的 agentic 语言世界模型框架,通过从历史交互轨迹重建环境世界书(world book)来模拟原始系统不可用的交互环境。在九个环境上的实验表明,其在下一观测保真度和长程交互一致性方面优于基于提示的传统语言世界模型。

Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce. We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation. We instantiate this paradigm with Trace2Env, a learning-free framework for settings where the original system is unavailable but historical interaction traces remain accessible. Trace2Env reconstructs these traces into a reusable environment worldbook containing environment schemas, grounded evidence, and induced behavioral knowledge. At runtime, the world model agent actively consults the worldbook together with persistent episodic state to infer each action's observation and lasting state effects. Across nine environments, Trace2Env improves both next-observation fidelity and long-horizon interaction consistency over conventional prompt-based LWMs. In multi-turn interaction, task agent actions generated against Trace2Env remain valid more often when replayed in the real environment, indicating that its simulated dynamics better preserve the consequences of earlier actions across successive turns. These results establish agentic language world modeling as an alternative direction for building realistic environment replicas without reconstructing the original executable system.
Original Article
View Cached Full Text

Cached at: 10/09/26, 06:27 AM

Paper page - From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation

Source: https://huggingface.co/papers/2610.06100

Abstract

RealisticenvironmentreplicasareincreasinglyvaluablefortrainingandevaluatingLLMagents,yettheoriginalsystemsmaybeinaccessibleorimpracticaltoreproduce.Weexploreagenticlanguageworldmodeling:ratherthanrebuildinganexecutableenvironment,aworldmodelagentservesastheenvironmentforataskagentandsupportsfaithfulandstatefulsimulation.WeinstantiatethisparadigmwithTrace2Env,alearning-freeframeworkforsettingswheretheoriginalsystemisunavailablebuthistoricalinteractiontracesremainaccessible.Trace2Envreconstructsthesetracesintoareusableenvironmentworldbookcontainingenvironmentschemas,groundedevidence,andinducedbehavioralknowledge.Atruntime,theworldmodelagentactivelyconsultstheworldbooktogetherwithpersistentepisodicstatetoinfereachaction’sobservationandlastingstateeffects.Acrossnineenvironments,Trace2Envimprovesbothnext-observationfidelityandlong-horizoninteractionconsistencyoverconventionalprompt-basedLWMs.Inmulti-turninteraction,taskagentactionsgeneratedagainstTrace2Envremainvalidmoreoftenwhenreplayedintherealenvironment,indicatingthatitssimulateddynamicsbetterpreservetheconsequencesofearlieractionsacrosssuccessiveturns.Theseresultsestablishagenticlanguageworldmodelingasanalternativedirectionforbuildingrealisticenvironmentreplicaswithoutreconstructingtheoriginalexecutablesystem.

View arXiv pageView PDFProject pageGitHub17Add to collection

Get this paper in your agent:

hf papers read 2610\.06100

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.06100 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.06100 in a dataset README.md to link it from this page.

Spaces citing this paper2

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Relational Learning as World Modeling

Hugging Face Daily Papers

论文提出 TabWM(表格世界模型)与 WorldRel 生成器,通过在上下文中观察执行样本来推断关系型系统的动态,预测动作导致的稀疏结构化编辑,从而将关系学习从状态建模扩展到世界建模与动作规划。

Qwen-AgentWorld: Language World Models for General Agents

Hacker News Top

Qwen-AgentWorld introduces language world models for agentic environments, covering seven domains with long chain-of-thought reasoning. The work includes a new benchmark, AgentWorldBench, and shows that world modeling improves downstream agent performance.

WM^MLLM: Turning MLLMs into World Models

Hugging Face Daily Papers

WM^MLLM 将多模态大语言模型改造为交互式世界模型,通过外部全景状态与修订历史实现从单张图像出发的持久、可编辑世界生成,支持精确重访与局部编辑,并在 MBench-A、CompBench、WBench 等基准上显著超越现有世界模型基线。