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
arXiv:2607. 01531v1 Announce Type: new Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.
By David Courtis, Wenhao Li, Scott Sanner
Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks. World models learned with deep networks are flexible but data-hungry and transfer poorly beyond their training distribution.
arXiv:2607. 01531v2 Announce Type: replace Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks.
By David Courtis, Wenhao Li, Scott Sanner
arXiv:2601.13247v2 Announce Type: replace-cross
Abstract: Current Large Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural ground...
By Baochang Ren, Yunzhi Yao, Rui Sun, Shuofei Qiao, Ningyu Zhang, Huajun Chen
arXiv:2608. 06015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (RL) is notoriously sample inefficient.
By Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction.
AgentGarten is a framework that links simulators and game engines with a shared neural renderer to create real‑time interactive virtual worlds. It uses a pretrained video model adapted to geometry conditions, refined with Adversarial Forcing, to produce realistic visual observations while maintaining consistent state and rules. The system enables agents to learn efficiently—achieving comparable performance in only four training rounds versus millions in traditional reinforcement learning—by distilling experience into playbooks that successive agents can inherit and improve upon.
By Jiawei Chi, Shangchen Miao, Zhiyuan Shi, Kailu Wu, Hanyang Wang, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jun Gao, Mingsheng Long, Yueqi Duan, Jiangran Lyu, Jialong Wu, Fangfu Liu
EvolvingBrain introduces an adaptive skill system that enables multi-modal agents to self‑evolve in open worlds. The system comprises Stratified Skill Self‑Evolution, which extracts procedural and problematic patterns from trajectories to build a multi‑granularity skill architecture, and State‑Aware Adaptive Execution, which uses structured memory to guide skill fusion based on the agent’s current state. Experiments on VAB‑Minecraft and DiscoveryWorld show improved success rates and generalization, with code available for public release.
By Runxuan Liu, Jingqi Shi, Baoxin Wang, Honghong Zhao, Haoyuan Xu, Yueqing Sun, Jiafeng Liang, Tao He, Dayong Wu, Qi Gu, Shijin Wang, Ming Liu, Bing Qin
MineExplorer is a benchmark designed to assess the open‑world exploration abilities of multimodal large language models (MLLMs) in Minecraft. It filters out tasks that rely heavily on Minecraft‑specific knowledge, organizes tasks into ReAct‑style capabilities, and composes atomic tasks into implicit multi‑hop challenges. A multi‑agent synthesis workflow creates reliable task graphs, sandbox scenes, and rule‑based milestone evaluators, and human evaluation confirms its superiority over a single‑agent baseline. Experiments show that while advanced MLLMs can handle many single‑hop tasks, they struggle with longer trajectories that require coordinating hidden prerequisites, and larger models or different thinking modes do not consistently improve performance.
By Tianjie Ju, Yueqing Sun, Zheng Wu, Wei Zhang, Yaqi Huo, Xi Su, Qi Gu, Xunliang Cai, Gongshen Liu, Zhuosheng Zhang
arXiv:2609.05576v1 Announce Type: new
Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across statefu...
By Yirong Zeng, Shen You, Jinhang Feng, Yufei Liu, Xiao Ding, Yutai Hou, Hao Cong, Yuxian Wang, Wu Ning, Wang Xu, Bibo Cai
arXiv:2606. 19990v1 Announce Type: new Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery.
By Pu Li, Zhigang Lin, Qiang Wu, Yongxuan Lv, Fei Wang, Shan You