Manual context attachment produces a combinatorial collapse in AI task-success probability as personal corpus size and multi-document conjunctivity grow, while dynamic retrieval is insulated from that collapse, creating an inequality dimension complementary to agentic access.
arXiv preprint arXiv:2602.22401 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Federation over Text lets agents collaboratively distill a shared metacognitive insight library from reasoning traces, improving multi-task performance ~25% and covering >80% of subsequent paper contributions.
citing papers explorer
-
The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality
Manual context attachment produces a combinatorial collapse in AI task-success probability as personal corpus size and multi-document conjunctivity grow, while dynamic retrieval is insulated from that collapse, creating an inequality dimension complementary to agentic access.
-
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Federation over Text lets agents collaboratively distill a shared metacognitive insight library from reasoning traces, improving multi-task performance ~25% and covering >80% of subsequent paper contributions.