ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
Long-horizon LLM tasks often fail not because a single answer is unattainable, but because knowledge states drift across rounds, intermediate commitments remain implicit, and interruption fractures the evolving evidence chain. This paper presents ADEMA as a knowledge-state orchestration architecture for long-horizon knowledge synthesis rather than as a generic multi-agent runtime. The architecture combines explicit epistemic bookkeeping, heterogeneous dual-evaluator governance, adaptive task-mod
Record details
Published: 28 April 2026
Source: arXiv
Category: Research
Topics: Regulation · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
arXiv · 28 April 2026
Agent Name Service (ANS): A Proof-of-Concept Trust Layer for Secure AI Agent Discovery, Identity, and Governance in Kubernetes
arXiv · 29 April 2026
ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable
arXiv · 28 April 2026
Decision Evidence Maturity Model for Agentic AI: A Property-Level Method Specification
arXiv · 29 April 2026
TDD Governance for Multi-Agent Code Generation via Prompt Engineering
arXiv · 29 April 2026
ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation
arXiv · 29 April 2026
How to cite this record
ethics.ai (28 April 2026), “ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents,” evidence record 5246, https://ethics.ai/record/5246 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.