WFM: Wiki Foundation Model for Complex Agentic Reasoning
cs.AI
Submitted: 2026-09-16
Updated: 2026-09-16
License: http://creativecommons.org/licenses/by/4.0/
The gist: Real-world agents fundamentally require persistent non-parametric knowledge for dynamic reasoning, i.e., long-term memory and retrieval-augmented generation.
Terminology
Abstract
Real-world agents fundamentally require persistent non-parametric knowledge for dynamic reasoning, i.e., long-term memory and retrieval-augmented generation. While graphs have shown reliable advantages in providing structured evidence, the sparse graph representations naturally restrict machine readability and semantic density required for complex agentic workflows. Driven by this limitation, the entire industry is witnessing a paradigm shift from traditional sparse graphs to LLM Wiki, an agent-native knowledge representation that couples dense document contexts with markdown files containing multi-layered topological linkages. However, parameterizing such rich semantics is challenging to encode dense textual contexts using traditional sparse graph embeddings. Moreover, learning LLM Wiki with existing graph encoders could overwhelm distributed system overheads that hinder deployment in large-scale commercial scenarios. To this end, we propose a novel paradigm Wiki Foundation Model, i.e., WFM, tailored for scalable, agent-native representation and retrieval. Specifically, (i) we formalize a Wiki Graph schema that seamlessly bridges fine-grained structures with dense contexts, maintaining explicit topologies alongside continuous semantics; (ii) A query-conditioned attentive aggregation is tailored for rich wiki message passing and explicit attention variance regularization; (iii) We engineer an infrastructural NCCL boundary exchange protocol that hoists static partition indices and leverages fixed-shape GPU-to-GPU collectives, bypassing CPU serialization and memory copy overheads. Extensive evaluations across five long-term agent memory and multi-hop reasoning benchmarks demonstrate the remarkable performance of WFM, while achieving a 10.5 times training acceleration on distributed clusters.
Sources
- Toward Native Multimodal Modeling: A Roadmap
- Qwen Technical Report
- Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
- CLR-Bench: Evaluating Large Language Models in College-level Reasoning
- Deep Tabular Research via Continual Experience-Driven Execution
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Retrieval-Augmented Generation for Large Language Models: A Survey
- LightRAG: Simple and Fast Retrieval-Augmented Generation
- Retrieval-Augmented Generation with Graphs (GraphRAG)
- Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Kimi K2.5: Visual Agentic Intelligence
- GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
- GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
- Graph Retrieval-Augmented Generation: A Survey
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation
- A-MEM: Agentic Memory for LLM Agents
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection