From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
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。
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
Agentic World Modeling for Agent Test-time Scaling without Environment Replica
论文提出 Agentic World Modeling(AWM),通过只读接口与真实环境交互式获取证据来模拟动作结果,实现无需环境副本的并行 agent 测试时扩展,在 τ-bench、AppWorld 和 OfficeBench 上显著优于单次模拟与训练式世界模型基线。
Relational Learning as World Modeling
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
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
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。
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
A comprehensive survey on agentic environment engineering for LLMs, covering environment modeling, synthesis, evaluation, and application, with a focus on agent-environment co-evolution.