Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Boxiu Li, Zimo Wen, Yijia Fan, Junxiang Lei, Sufeng Guo, Jiaao Wu, Ruize Tang, Mukai Li, Yifei Shen, Xiaoyu Chen, Wanbo Zhang, Runjing Gu, Yifei Gao, Yuheng Wu, Xuyao Huang, Zelong Zhao, Jiachen Zhang, Shibo Hu, Hangxi Guo, Yilin Chen, Yuzhe Zhang, Fan Yang, Chuan Wen, Xian Zhang, Xuanhe Zhou, Zhijie Deng
• Venue: arXiv: cs.AI
• Published: 2026-08-05
• Collected: 2026-08-06
• URL: http://arxiv.org/abs/2608.05144v1
• PDF: https://arxiv.org/pdf/2608.05144v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces Argus, a persistent, self-evolving runtime system designed for long-horizon reasoning. Argus consists of Manager, Planner, Engineer, and Reviewer that execute bounded missions over durable project state. It achieves impressive results in seven GPT-5.5 benchmark arenas, outperforming Direct Copilot, and shows potential for future supervised and reinforcement learning.

What the Document Says

• Argus is a persistent, self-evolving runtime system
• It consists of Manager, Planner, Engineer, and Reviewer
• These components execute bounded missions over durable project state
• Argus separates stable user intent from operational objectives, constraints, and verification criteria
• It admits memories, skills, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and task-native verification
• Model weights remain fixed in Argus
• Self-evolution occurs through persistent runtime state and control policy
• Autonomous execution between operator-owned escalation points is possible
• In seven GPT-5.5 benchmark arenas, Argus achieves about 78% on SWE-Bench Pro compared to 59% for Direct Copilot while using 1.41 times the aggregate tokens
• After verification-gated self-evolution, mature SWE-Bench waves use 21% fewer solve-input tokens and 15% less active workflow time per task than startup waves
• Argus also achieves 76.8% on AARRI-Bench and a 28.0-point gap on mathematical data synthesis

Key Concepts Mentioned

• Argus
• long-horizon reasoning
• persistent runtime
• self-evolving
• Manager
• Planner
• Engineer
• Reviewer
• GPT-5.5 benchmark arenas

Claims Made by the Document

• Argus can revise, recover, and accumulate verified approaches
• Argus produces structured trajectories for future supervised and reinforcement learning

Evidence Used

• Results from seven GPT-5.5 benchmark arenas
• Reduction in solve-input tokens and active workflow time per task after self-evolution
• High performance on AARRI-Bench and mathematical data synthesis

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / 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, procedures, verifiers, routing decisions, and rejected routes only after role-owned review and, when available, task-native verification. Model weights remain fixed; self-evolution occurs through persistent runtime state and control policy, with autonomous execution between operator-owned escalation points. Across seven GPT-5.5 benchmark arenas, Argus achieves about 78% on SWE-Bench Pro versus 59% for Direct Copilot while using 1.41 times the aggregate tokens. After verification-gated self-evolution, mature SWE-Bench waves use 21% fewer solve-input tokens and 15% less active workflow time per task than startup waves, while recording 34 verifier recoveries and 22 strict review-loop rescues. Argus also reaches 76.8% on AARRI-Bench and a 28.0-point gap on mathematical data synthesis, with competitive GPU-kernel and language-model-training results. Beyond benchmarks, an optimized RWKV6 kernel was merged upstream; a multi-day mathematics campaign retained falsified routes and proof-backed frontier updates; and six paper pipelines completed 254 missions with 16 stage rollbacks. These results show that a fixed-weight, self-evolving harness can revise, recover, and accumulate verified approaches while producing structured trajectories for future supervised and reinforcement learning.