# DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents > Source: > Published: 2026-10-22 03:30:16+00:00 Language-model agents that run long tasks often redo work they have already done: they re-issue a tool call they made earlier and get back exactly the same observation, a step that adds no new information. We identify this failure as a loop. Loops appear natively in Qwen, Llama, and Gemini agents an