cs.AINov 18, 2026

Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow

Authors: Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Qi Liu

Organizations: University of Science and Technology of China · Nanyang Technological University

Abstract

Autonomous LLM agents incur substantial cost and latency by invoking a large model (System-2) at every step, even when many intermediate actions choose among a small set of known candidates. Existing dual-system agents offload such decisions to a lightweight System-1 model, but rely on workflow-specific hooks authored per environment. We present AnyS1, a framework that turns human-authored procedural skills, whose instructions naturally specify where choices arise and which options apply, into a shared, domain-general source of decision points. Offline, AnyS1 mines grounded enumerable decisions across over 1,000 public skills, gathers execution-grounded trajectory states inside isolated containers to construct Any-DP, and trains a single calibrated 4B pointer System-1 with label smoothing. At run time, compiled workflows resolve routine decisions in one forward pass and fall back to System-2 when confidence falls below a calibrated threshold. Across three unseen benchmarks and distinct System-2 model families, AnyS1 preserves task reliability while cutting episode cost by 75-91% and model-call time by 63-92% relative to an uncompiled System-2 agent, and maintains performance under zero-shot threshold transfer.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. System1-Arena: Which Decisions Can Be Left to System 1?

    Oct 15, 2026Tianyu Chen, Xinyang Liu, Ruyi An +2LLM Decision-MakingLLM Evaluation

  2. TabAgent: Distilling LLM Agent Components into Cheap Classifiers

    Feb 18, 2026Ido Levy, Segev Shlomov, Avi Yaeli +5LLM Agent Workflow OptimizationAI Agent Architecture