LongHorizon-Harness proposes Manage-Execute-Audit loop for long-horizon agents
Proposes a Manage-Execute-Audit (MEA) loop that separates task-state tracking from execution, using a manager to hold verified task state, a fresh-context executor per subtask, and a read-only auditor to check environment state before each new round. Reported gains include Qwen 3.7-Plus rising from 51.8% to 80.7% on WeaveBench and Claude Opus 4.7 rising from 20.0% to 34.3% on an OSWorld 2.0 subset.
Why it matters
On HuggingFace Daily Papers with reported upvotes above 100, indicating strong community interest in fixing long-horizon agent reliability by decoupling state tracking from execution.
Importance: 3/5
HF Daily Papers with >=100 upvotes bump applied.
Sources
official
Paper page - LongHorizon-Harness