Related papers: On Immutable Memory Systems for Artificial Agents:…
Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing privacy-preserving machine learning (ppML) techniques, such as Differential Privacy (DP) and…
Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…
The scalability of blockchain technology remains a pivotal challenge, impeding its widespread adoption across various sectors. This study introduces an innovative approach to address this challenge by proposing the adaptive restructuring of…
Shannon's information theory deliberately excludes message semantics. This paper develops a rigorous framework for semantic communication that integrates formal proof systems with Shannon-theoretic tools. We introduce an axiomatic…
We propose the Agent Economy, a blockchain-based foundation where autonomous AI agents operate as economic peers to humans. Current agents lack independent legal identity, cannot hold assets, and cannot receive payments directly. We…
Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and…
Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…
Transformers, while powerful, suffer from quadratic computational complexity and the ever-growing Key-Value (KV) cache of the attention mechanism. This paper introduces Trellis, a novel Transformer architecture with bounded memory that…
Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic…
Current language model systems remain fundamentally stateless across sessions, limiting their ability to personalize interactions over time. While retrieval-augmented generation and fine-tuning improve knowledge access and domain…
Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing…
The "black box" nature of Large Reasoning Models (LRMs) presents critical limitations in reliability and transparency, fueling the debate around the "illusion of thinking" and the challenge of state hallucinations in agentic systems. In…
Modern engineered systems increasingly involve complex sociotechnical environments where multiple agents, including humans and the emerging paradigm of agentic AI powered by large language models, must navigate social dilemmas that pit…
Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…
Retrieval-Augmented Generation (RAG) and vector-based search have become foundational tools for memory in AI systems, yet they struggle with abstraction, scalability, and semantic precision - especially in decentralized environments. We…
This article provides an analytical framework for how to simulate human-like thought processes within a computer. It describes how attention and memory should be structured, updated, and utilized to search for associative additions to the…
This paper addresses the critical challenge of mesa-optimization in AI safety by providing a formal definition of agency and a framework for its analysis. Agency is conceptualized as a Continuous Representation of accumulated experience…
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…
Blockchain technology has emerged as a transformative paradigm for decentralized and secure data management across diverse application domains, including healthcare, supply chain management, and the Internet of Things. Its core features,…