GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning

arXiv:2608.22479 · cs.CL, cs.LG · Submitted 2026-08-23 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-08-23

Updated: 2026-08-30

Code: https://github.com/cjcj46262/GTA-RAG

Terminology

• RAG — 56× in this paper · explained in 3 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• GRPO Objective — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Graph Construction — 2× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Semantic Similarity — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Data Augmentation — 1× in this paper · explained in 7 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Hypergraph — 1× in this paper · explained in 2 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• PopQA and Natural Questions — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes

Sources

• LightRAG: Simple and Fast Retrieval-Augmented Generation
• Qwen2.5-Coder Technical Report
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning
• Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
• Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
• When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
• NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
• A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering