Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

Hugging Face Daily Papers Papers
scientific-ai lab-notes agent-skills certainty-preservation ai-agents framework research

Summary

Notes2Skills is a two-stage framework that converts laboratory notes into verifiable skills for AI agents while preserving author uncertainty, enabling safer scientific AI systems.

Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level. However, most prior work on scientific text focuses on papers, protocols, or structured databases, leaving informal laboratory notes underexplored as inputs to AI agents for science. This gap matters because lab notes often intermingle validated observations, tentative judgments, and possible experimental next steps within the same passage. If these signals are conflated, an AI agent may mistake uncertain scientific judgments for confirmed conclusions or executable actions. To this end, we present Notes2Skills, a two-stage framework for turning lab notebooks into verifiable skills for scientific AI agents while preserving the author's certainty. Across seven conditions and three wet-lab sessions, Notes2Skills is the only configuration that neither mistakes uncertain notes for firm instructions nor discards firm ones. We show that certainty preservation is the missing piece between lab notebooks and reliable agent skills, opening a path toward safer AI co-scientist systems.
Original Article
View Cached Full Text

Cached at: 06/23/26, 09:41 AM

Paper page - Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

Source: https://huggingface.co/papers/2606.11897

Abstract

Notes2Skills framework converts laboratory notes into verifiable skills for AI agents while maintaining author uncertainty levels, addressing gaps in scientific AI development.

Scientific discovery workflowsusually contain and rely heavily onlab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informativelab notespreserve evolvingscientific reasoningandauthor uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level. However, most prior work on scientific text focuses on papers, protocols, or structured databases, leaving informal laboratory notes underexplored as inputs toAI agentsfor science. This gap matters becauselab notesoften intermingle validated observations, tentative judgments, and possible experimental next steps within the same passage. If these signals are conflated, an AI agent may mistake uncertain scientific judgments for confirmed conclusions or executable actions. To this end, we present Notes2Skills, a two-stage framework for turning lab notebooks intoverifiable skillsforscientific AIagents while preserving the author’s certainty. Across seven conditions and three wet-lab sessions, Notes2Skills is the only configuration that neither mistakes uncertain notes for firm instructions nor discards firm ones. We show thatcertainty preservationis the missing piece between lab notebooks and reliable agent skills, opening a path toward safer AI co-scientist systems.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.11897

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.11897 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.11897 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.11897 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SkillGen: Verified Inference-Time Agent Skill Synthesis

arXiv cs.LG

This article introduces SkillGen, a multi-agent framework that synthesizes and verifies reusable inference-time skills for LLM agents by contrasting successful and failed trajectories. The method ensures skills are auditable and empirically verified for their net positive impact on agent performance.