ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents

arXiv:2604.25849v1 Announce Type: new Abstract: 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, heterogene