# GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding

arXiv: https://arxiv.org/abs/2508.12379 · HTML: https://mlsanity.com/paper/2508.12379/

## Key facts

- Cited by 9 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 14 of its 41 references that are in the map.
- First posted on arXiv 17 Aug 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, 14 of 14)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability](https://mlsanity.com/paper/2403.04483/) (2024)
- [InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment](https://mlsanity.com/paper/2402.08785/) (2024)
- [GraphArena: Evaluating and Exploring Large Language Models on Graph Computation](https://mlsanity.com/paper/2407.00379/) (2024)
- [EventGPT: Event Stream Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2412.00832/) (2024)
- [Working Memory Capacity of ChatGPT: An Empirical Study](https://mlsanity.com/paper/2305.03731/) (2023)
- [GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction](https://mlsanity.com/paper/2412.12152/) (2024)
- [GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2407.02936/) (2024)

## Built on by (most cited first, 9 of 9)

- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [TeleMem: Building Long-Term and Multimodal Memory for Agentic AI](https://mlsanity.com/paper/2601.06037/) (2025)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation](https://mlsanity.com/paper/2510.04838/) (2025)
- [DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering](https://mlsanity.com/paper/2510.12251/) (2025)
- [RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents](https://mlsanity.com/paper/2605.13391/) (2026)
- [NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval](https://mlsanity.com/paper/2511.14096/) (2025)
- [Multi-Agent Agentic Graph Learning via Structural Signatures](https://mlsanity.com/paper/2609.09565/) (2026)
- [Are Large Language Models Suitable for Graph Computation? Progress and Prospects](https://mlsanity.com/paper/2606.06865/) (2026)

## Abstract (arXiv)

Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their inability to retain long-range graph topology over extended contexts while sustaining coherent multi-step reasoning. However, real-world graphs are often structurally complex, such as Web, Transportation, Social, and Citation networks. To address these limitations, we propose GraphCogent, a collaborative agent framework inspired by human Working Memory Model that decomposes graph reasoning into specialized cognitive processes: sense, buffer, and execute. The framework consists of three modules: Sensory Module standardizes diverse graph text representations via subgraph sampling, Buffer Module integrates and indexes graph data across multiple formats, and Execution Module combines tool calling and tool creation for efficient reasoning. We also introduce Graph4real, a comprehensive benchmark that contains four domains of real-world graphs (Web, Transportation, Social, and Citation) to evaluate LLMs' graph reasoning capabilities. Our Graph4real covers 21 different graph reasoning tasks, categorized into three types (Structural Querying, Algorithmic Reasoning, and Predictive Modeling tasks), with graph scales up to 10 times larger than existing benchmarks. Experiments show that Llama3.1-8B based GraphCogent achieves a 50% improvement over massive-scale LLMs like DeepSeek-R1 (671B). Compared to state-of-the-art agent-based baseline, our framework outperforms by 20% in accuracy while reducing token usage by 80% for in-toolset tasks and 30% for out-toolset tasks. Code will be available after review.