paper-with-me

Papers

AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning

2025-12-28 · Shihao Cai, Runnan Fang, Jialong Wu, Baixuan Li, Xinyu Wang, Yong Jiang, Liangcai Su, Liwen Zhang, Wenbiao Yin, Zhen Zhang, Fuli Feng, Pengjun Xie, Xiaobin Wang arxiv

Conducting reinforcement learning (RL) in simulated environments offers a cost-effective and highly scalable way to enhance language-based agents. However, previous work has been limited to semi-automated environment synthesis or tasks lacking sufficient difficulty, offering little breadth or depth. In addition, the instability of simulated users integrated into these environments, along with the heterogeneity across simulated environments, poses further challenges for agentic RL. In this work, we propose: (1) a unified pipeline for automated and scalable synthesis of simulated environments associated with high-difficulty but easily verifiable tasks; and (2) an environment level RL algorithm that not only effectively mitigates user instability but also performs advantage estimation at the environment level, thereby improving training efficiency and stability. Comprehensive evaluations on agentic benchmarks, including tau-bench, tau2-Bench, and VitaBench, validate the effectiveness of our proposed method. Further in-depth analyses underscore its out-of-domain generalization.

📄 PDF Abstract BibTeX arXiv:2512.22857

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningDomain Generalization

Similar Papers 제목 키워드 기반

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

2026-01-29 · Xiaoyu Tian, Haotian Wang, Shuaiting Chen, Hao Zhou 외 arxiv

Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing methods still require manual intervention, d…

Reinforcement LearningDecision Making

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

2026-05-18 · Minrui Xu, Zilin Wang, Mengyi DENG, Zhiwei Li 외 arxiv

Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data…

Reinforcement Learning

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

2026-06-10 · Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao 외 arxiv

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, ex…

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

2026-02-27 · Weinan Dai, Hanlin Wu, Qiying Yu, Huan-ang Gao 외 arxiv

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) rema…

Reinforcement LearningCode Generation

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

2026-06-30 · Keyu Zhao, Lingyan Kong, Fengli Xu, Yong Li arxiv

Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. However, existing approaches predominantly rely on pre-defined agentic …

Logical Reasoning