The paper introduces "environment evolution," a method that incrementally raises the difficulty of interactive environments for terminal agents using off‑policy updates. It derives three evolution directions tied to a multi‑turn learning objective and implements them via a loop‑engineered multi‑agent harness. Experiments with models such as Hy4 preview, Claude Opus 5, GPT‑5.6 Sol, Qwen3.6‑27B, and Qwen3.6‑35B‑A3B demonstrate that this approach consistently generates harder environments and yields significant performance gains on Terminal‑Bench 2.1.
arXiv:2606. 03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static.
By Guhong Chen, Yingcheng Shi, Yongbin Li, Binhua Li, Xander Xu, Hu Wei, Shiwen Ni, Min Yang, Jieping Ye
arXiv:2607. 10891v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs).
By Qijia Shen, Zhiqi Huang, Vamsidhar Kamanuru, Aznaur Aliev, Jay Rainton, Ahmed Awelkair, Zhichen Zeng, Jiajun Li, Shi Dong, Yueming Yuan, Boyuan Ma, Qizheng Zhang, Jiwei Fu, Yuzhen Mao, Wendong Fan, Ping Nie, Philip Torr, Bernard Ghanem, Changran Hu, Jonathan Lingjie Li, Urmish Thakker, Guohao Li
arXiv:2607. 21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization.
By Yipeng Shi, Zhipeng Ma, Yue Wang, Qitai Tan, Yang Li, Peng Chen, Zhengzhou Zhu
arXiv:2606. 20324v1 Announce Type: cross Abstract: Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior.
By Xiaoran Liu, Istvan David
arXiv:2606. 14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts.
By Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng, Hanlin Teng, Tianhao Li, Chao Li, Xule Liu, Jian Liang, Zhizhong Zhang, Yuan Xie, Heng Qu, Kun Shao, Jian Luan
Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.
By Zhi Zheng, Rongsheng Chen, Yunpeng Ba, Zhenkun Wang, Yee Whye Teh, Wee Sun Lee
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
arXiv:2606. 02372v1 Announce Type: new Abstract: Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution.
By Youwei Liu, Jian Wang, Hanlin Wang, Wenjie Li
arXiv:2606. 17680v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful paradigm for training Large Language Models (LLMs) as agents.
By Zhitong Wang, Songze Li, Hao Peng, Shuzheng Si, Yi Wang, Maosong Sun, Juanzi Li
SPADE (Self-Play in Adaptive Synthetic Executable Environments) is a reinforcement‑learning framework where a single large language model acts as both an Environment Designer—creating executable, long‑horizon training environments—and a Reasoning Agent—learning to act within those environments. The framework uses a regret signal based on the difference between rewarded performance with and without privileged hints to guide the Designer toward environments that are challenging yet solvable. Experiments show that, when scaled to 30‑billion‑parameter models, SPADE outperforms fixed‑environment baselines by significant margins across math, science, code, and reasoning benchmarks, and improves tool‑use performance on BFCL‑v4 and ACEBench‑Agent.
whyItMatters":"By making environment design a learnable component, SPADE enables continuous self‑improvement and demonstrates that adaptive, self‑generated training environments can substantially boost language‑model performance across diverse tasks."
By Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.