Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow
Abstract
AnyS1 converts procedural skills into shared decision points, trains a small calibrated pointer model to resolve routine choices, and falls back to a large model when uncertain, reducing cost and latency while preserving reliability.
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.
Community
Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow
Where this lands in production is the candidate list. The whole bet is that decision points are enumerable from human-authored skill docs, and the steps that cost me the most are the ones where the right option isn't in the list at all — the tool returned something nobody planned for. Escalating those to System-2 at runtime is exactly where the latency win evaporates, since you've already paid for the fast pick plus the slow rescue. So I want two numbers: the fraction of real trajectory steps that are genuinely enumerable, measured on logs rather than on the tasks the docs were written for, and what end-to-end success does when the System-1 pick is wrong. A wrong pick that keeps going with no reasoning trace to read is a worse failure mode than a slow correct step — at least the slow one leaves you something to debug.
Thank you for your comments on our research. Regarding the first issue, we have already presented the relevant experimental results in the paper (first, E nodes can be extracted from most real-world skills; second, in the experiments, the system 1 model has higher accuracy on these nodes). As for the second issue, I will consider adding it later.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Think Before You Act: Decision Gate for LLM Agents (2026)
- ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows (2026)
- How Much Skill Orchestration Can LLM Agents Compile Away? Execution-Grounded Specialization for Token-Efficient Skill Use (2026)
- ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents (2026)
- System1-Arena: Which Decisions Can Be Left to System 1? (2026)
- Learning What to Skip: Counterfactual Credit Assignment for Efficient Multi-Agent LLM Workflows (2026)
- Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.23751 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 1
smSquirrel/SkillDP
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper