← Back to all news
arXiv AI By Xinjie Shen, Wei Fan, Xudong Guo, Jianhong Tu, Yang Su, Chuqiao Kuang, Yinger Zhang, Dayiheng Liu

Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms

Read the original on arXiv AI →

The paper introduces VHD-Play, a pipeline that first samples and solves a mathematical model before generating agentic reinforcement learning environments, ensuring that dynamics and evaluation are aligned from the outset. This approach yields 3,300 diverse environments at a low cost and significantly improves the performance of a large language‑model agent (Qwen3.6‑35B‑A3B) across multiple diagnostic families and external benchmarks. The study demonstrates that stateful interaction is a key factor in learning gains and that scaling the training substrate can further enhance performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Sep 10

Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective

arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explora...

By Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Ruochen Zhou, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li
llmsagentsreinforcement-learningfine-tuning
More like this →
arXiv Computation and Language
Sep 14

LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?

LLM‑BabyBench transforms the BabyAI gridworld into a fully observable, purely textual setting that isolates planning as the sole source of failure. By serialising the entire grid, providing formal instructions, and validating actions deterministically, the benchmark introduces the PPD suite—Predict, Plan, and Decompose tasks—each scored with metrics that separate mission understanding from sequencing. Across a range of large language models, simulation accuracy is high while planning success drops sharply beyond a model‑specific horizon, revealing that plan length—not grid size—drives failure and that models often commit to a single corridor‑shaped route without backtracking.

By Idriss Malek, Omar Choukrani, Daniil Orel, Anh Duy Le Dinh, Zhuohan Xie, Zangir Iklassov, Martin Tak\'a\v{c}, Salem Lahlou
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 4

CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents

CoMAP introduces a framework that jointly evolves textual world models and agent policies through a closed‑loop interaction. At each decision step the world model forecasts future state feedback for candidate actions, while the agent reflects on the reliability of this feedback to refine its action. The resulting on‑policy trajectories are used to self‑distill and update the world model, improving prediction accuracy and long‑horizon decision‑making across embodied planning, web navigation, and tool‑use benchmarks.

By Youwei Liu, Jian Wang, Hanlin Wang, Wenjie Li
llmsagentsroboticsefficiencybenchmarks
More like this →