This work formalizes a Wiki Graph schema that seamlessly bridges fine-grained structures with dense contexts, maintaining explicit topologies alongside continuous semantics and 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.
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.
Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training.
Shi-Long Liu, Yongqiang Liu, Jiye Liu et al.· Proceedings of the 32nd ACM...· 0 citations
A hybrid knowledge graph generation pipeline that grounds a Large Language Model in the Wikidata multilingual Knowledge Graph while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata to generate a comprehensive skills knowledge graph.
Emma Jouffroy, Warren Jouanneau, Marc Palyart· 0 citations
RACER employs a semantic-aware action pruning and teacher-guided reinforcement learning mechanism to efficiently extract high-quality reasoning pathways from large-scale KGs, and introduces a cross-task accumulated shared memory graph paired with an attention-driven multi-path knowledge refinement module.
Yuwei Lou, Hao Hu, Yu-Zhou Jiang et al.· 1 citation
GraMRAG is proposed, a graph memory-guided multi-agent RAG framework that integrates a dynamic multimodal memory graph to enable stable, multi-step multimodal reasoning and introduces a vision-text bridged reasoning paradigm that unifies multi-scale entity cropping with a ReAct-style visual toolchain, enhancing the lon...
Recent advances in large language model (LLM) agents have shown promise for autonomous decision-making in recommender systems. However, existing approaches suffer from two fundamental limitations: flat agent memories that conflate different information modalities and prohibitive computational costs that prevent scaling...
Ivan Bulychev, Andrey V. Savchenko· Applied Informatics· 0 citations
This work proposes HyperSkill, a hypergraph-based memory framework that jointly improves what to store, how memory is structured and retrieved, and how memory evolves, and represents memory as a hypergraph with two node types, subtask steps and reusable skills.