Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
Introduces a novel architecture for persistent agentic reasoning with fixed model weights, addressing core challenges in autonomous long-term task execution.
AI Summary
Researchers present Argus, a persistent agentic runtime for long-horizon reasoning that achieves ~78% on SWE-Bench Pro using GPT-5.5 while evolving through runtime state rather than weight updates.
Excerpt
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and pivot when measurements reveal failure, hidden constraints, or a misspecified objective. We present Argus, a persistent, self-evolving runtime in which Manager, Planner, Engineer, and Reviewer execute bounded missions over durable project state. Argus separates stable user intent from operational objectives, constraints, and verification criteria, and admits memories, skills, proce