SOURCE-LINKED INTELLIGENCE

Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions using approximately 14x and 15x fewer input tokens (by reader) and at 5-7x lower cost than a budget-c

Read original source ↗ Open in workspace

recordType

paper

region

Global