@inproceedings{sun-etal-2026-agentgl,
    title = "{A}gent{GL}: Towards Agentic Graph Learning with {LLM}s via Reinforcement Learning",
    author = "Sun, Yuanfu  and
      Li, Kang  and
      Fan, Dongzhe  and
      Liu, Jiajin  and
      Tan, Qiaoyu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1161/",
    pages = "25313--25335",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Language Models (LLMs) increasingly rely on agentic capabilities{---}iterative retrieval, tool use, and decision-making{---}to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL){--}driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5{\%} in node classification and 28.4{\%} in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at \url{ https://github.com/sunyuanfu/AgentGL}."
}