AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning

arXiv:2604.05846v2 Announce Type: replace 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 https://github.com/sunyuanfu/AgentGL.

Related

• AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin
• Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
• FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
• CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
• Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization
• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation

Source: arXiv cs.CL | 2026-04-24