arXiv cs.MA· Wendi Li, Huseyin A. Inan, Wei-Ning Chen, Yanzhi Chen, Chetan Bansal, Saravan Rajmohan, Sharon Li·· 11 小时前AI 评分38
Agentic World Modeling：无需环境副本的智能体测试时扩展
Agentic World Modeling for Agent Test-time Scaling without Environment Replica
AI 导读
研究者提出 Agentic World Modeling（AWM），将下一观测预测重构为多轮证据获取任务，让智能体模拟器通过安全只读接口查询真实环境并构建观测，从而在单一共享环境上实现并行轨迹探索。
正文 · 原文
Abstract:Test-time scaling (TTS) improves large language model agents by sampling and selecting among multiple candidate trajectories, but common realizations assume that these trajectories can be executed in parallel. This assumption breaks in realistic deployments, where enterprise workspaces and cloud services are shared and persistent, costly or infeasible to replicate, and actions may introduce irreversible side effects or cross-trajectory interference. Existing generative world models avoid direct execution, but typically compress environment state into a single prompt, limiting their ability to reliably simulate transitions under partial observability. Instead, we introduce Agentic World Modeling (AWM), which reformulates next-observation prediction as a multi-turn evidence-acquisition task. For each hypothetical action, an agentic simulator adaptively queries the real environment through safe read-only interfaces, reasons over the returned evidence, and uses executable computation to construct the resulting observation without mutating shared state. Integrated with trajectory-level TTS, AWM enables parallel exploration over a single shared environment. Across $\tau$-bench, AppWorld, and OfficeBench, AWM outperforms a single-shot simulation baseline by 40.07% on average, and surpasses a trained world-model baseline by 12.36% on average. These results establish interactive, read-grounded simulation as a practical foundation for safe and scalable agentic test-time scaling in shared, non-resettable environments.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.40927 [cs.AI] |
| (or arXiv:2610.40927v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40927 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wendi Li [view email]
[v1]
Thu, 29 Oct 2026 19:55:18 UTC (2,993 KB)
来源：arXiv cs.MA · arxiv.org