# Agentic-KGR: Co-evolutionary Knowledge Graph Construction through Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.09156 · HTML: https://mlsanity.com/paper/2510.09156/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization](https://mlsanity.com/paper/2505.15107/) (2025)
- [FlowReasoner: Reinforcing Query-Level Meta-Agents](https://mlsanity.com/paper/2504.15257/) (2025)
- [Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2507.21892/) (2025)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.17005/) (2025)
- [Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward](https://mlsanity.com/paper/2508.12800/) (2025)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [AutoKG: Efficient Automated Knowledge Graph Generation for Language Models](https://mlsanity.com/paper/2311.14740/) (2023)
- [MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster](https://mlsanity.com/paper/2507.19017/) (2025)
- [Knowledge Graph Reasoning with Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2405.13640/) (2024)
- [Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications](https://mlsanity.com/paper/2507.16507/) (2025)

## Built on by (most cited first, 1 of 1)

- [MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs](https://mlsanity.com/paper/2605.10064/) (2026)

## Abstract (arXiv)

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present Agentic-KGR, a novel framework enabling co-evolution between LLMs and knowledge graphs (KGs) through multi-round reinforcement learning (RL). Our approach introduces three key innovations: (1) a dynamic schema expansion mechanism that systematically extends graph ontologies beyond pre-defined boundaries during training; (2) a retrieval-augmented memory system enabling synergistic co-evolution between model parameters and knowledge structures through continuous optimization; (3) a learnable multi-scale prompt compression approach that preserves critical information while reducing computational complexity through adaptive sequence optimization. Experimental results demonstrate substantial improvements over supervised baselines and single-round RL approaches in knowledge extraction tasks. When integrated with GraphRAG, our method achieves superior performance in downstream QA tasks, with significant gains in both accuracy and knowledge coverage compared to existing methods.