Toward Knowledge-Centric AI: Discovering, Internalizing, and Using Explicit Knowledge Across Agents and Generations
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
License: http://creativecommons.org/licenses/by/4.0/
The gist: Knowledge is how understanding accumulates across people and generations: durable records that outlive their producers and that others can check, combine, teach, and correct.
Terminology
Abstract
Knowledge is how understanding accumulates across people and generations: durable records that outlive their producers and that others can check, combine, teach, and correct. AI agents are now built and run by many independent users and organizations, and each agent is upgraded, replaced, or retired within months. Yet what an agent learns stays trapped in model parameters, a transient context window, or a system-specific memory store that is appended to and retrieved from rather than processed. We argue that the next generation of AI should be knowledge-centric, built around an explicit, continuously evolving knowledge layer independent of any single agent. In this loop, agents discover knowledge from their environments and trajectories; the layer internalizes it by turning fragmented, heterogeneous records and experience into composable, revisable understanding; and agents across systems and generations use the result and return new outcomes for revision. While discovery and use have advanced rapidly with large language model agents, internalization remains the bottleneck. We argue that internalization should become a persistent object of training and maintenance-centered on condition-preserving conceptualization of events and deductive, inductive, and abductive reasoning across noisy, heterogeneous representations (text, tables, graphs, rules, and programs). To power this layer, we call for knowledge foundation models that provide shared neural capacity for knowledge computation, and outline a research agenda showing how an explicit knowledge layer delivers reuse, cost efficiency, auditability, and continuity across agent generations.
Sources
- Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
- Chronos-2: From Univariate to Universal Forecasting
- Complex Query Answering with Neural Link Predictors
- Top Ten Challenges Towards Agentic Neural Graph Databases
- Memory Layers at Scale
- Abductive Commonsense Reasoning
- Text-to-LoRA: Instant Transformer Adaption
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- GraphPFN: A Prior-Data Fitted Graph Foundation Model
- Retrieval-Augmented Generation for Large Language Models: A Survey
- KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning
- One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs
- Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- Towards In-Parameter Memory Augmentation for Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents