# SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows

arXiv: https://arxiv.org/abs/2606.08049 · HTML: https://mlsanity.com/paper/2606.08049/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Builds on (most cited first, 30 of 31)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs](https://mlsanity.com/paper/2210.12283/) (2022)
- [Autoformalization with Large Language Models](https://mlsanity.com/paper/2205.12615/) (2022)
- [OS-Copilot: Towards Generalist Computer Agents with Self-Improvement](https://mlsanity.com/paper/2402.07456/) (2024)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control](https://mlsanity.com/paper/2306.07863/) (2023)
- [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://mlsanity.com/paper/2309.11436/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments](https://mlsanity.com/paper/2501.10893/) (2025)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [Contextual Experience Replay for Self-Improvement of Language Agents](https://mlsanity.com/paper/2506.06698/) (2025)
- [CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation](https://mlsanity.com/paper/2501.16609/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution](https://mlsanity.com/paper/2401.13996/) (2024)
- [AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems](https://mlsanity.com/paper/2511.00628/) (2025)
- [DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation](https://mlsanity.com/paper/2503.07044/) (2025)
- [ReUseIt: Synthesizing Reusable AI Agent Workflows for Web Automation](https://mlsanity.com/paper/2510.14308/) (2025)
- [Bridging the Prototype-Production Gap: A Multi-Agent System for Notebooks Transformation](https://mlsanity.com/paper/2511.07257/) (2025)
- [AgentBay: A Hybrid Interaction Sandbox for Seamless Human-AI Intervention in Agentic Systems](https://mlsanity.com/paper/2512.04367/) (2025)

## Built on by (most cited first, 3 of 3)

- [ADIAS: Automated Design of Interactive Agentic Systems](https://mlsanity.com/paper/2608.06410/) (2026)
- [Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees](https://mlsanity.com/paper/2607.28399/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

AI agents increasingly turn past experience into reusable artifacts such as code, workflows, and procedural memories. Reuse can improve efficiency, but it also creates a lifecycle reliability problem: artifacts that succeed once may fail under environment drift, underspecified tasks, or changing task distributions, especially in web automation. We introduce SKILL.nb, a framework for governing reusable agent workflows with evidence-calibrated lifecycle policies. SKILL.nb uses selective formalization: execution evidence decides which workflow steps should become executable code, which should remain natural-language guided, and when those choices should be revised. Workflows are stored as auditable, versioned notebooks that interleave natural-language guidance, multi-language executable cells, validation gates, fallback paths, and multimodal evidence such as outputs, screenshots, and error traces. At runtime, gate-conditioned execution lets each step run code when its gates validate, or fall back locally when drift invalidates the executable realization. On WebArena-Verified, SKILL.nb achieves 53.7% single-round success, improving over the strongest baseline by 3.9 percentage points. Across three re-executions, it retains 91.7% of initially successful tasks, 15.5 points above the next best method. Under bounded repair, it recovers 72.9% of subsequent failures while limiting post-repair regressions to 4.2%, compared with 15.0% to 17.0% for persistent baselines. It also leads on Mind2Web cross-website and cross-domain splits. In a GitLab migration test, SKILL.nb preserves performance when reusing frozen state learned on GitLab 15.7, with frozen-versus-fresh target-version gaps of -1.7 points on GitLab 16.11 and +0.6 points on GitLab 18.9. These results identify lifecycle governance and gate-conditioned execution as reliability axes beyond one-shot task success.