# Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation

arXiv: https://arxiv.org/abs/2512.20278 · HTML: https://mlsanity.com/paper/2512.20278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 6 of 6)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [DynaSaur: Large Language Agents Beyond Predefined Actions](https://mlsanity.com/paper/2411.01747/) (2024)
- [Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments](https://mlsanity.com/paper/2509.20386/) (2025)
- [CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory](https://mlsanity.com/paper/2512.15813/) (2025)

## Abstract (arXiv)

While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate remains underexplored. This paper operationalizes the transition of Large Language Models from passive tool-users to active workflow architects. Through a high-fidelity case study of a cross-service orchestration task involving Outlook and OneDrive, we identify and address four structural bottlenecks in automated skill generation: the Discovery Gap involving navigation of large tool registries, the Verification Gap regarding grounding tool response structures, the Decomposition Gap which replaces inefficient search with Linear State Anchoring, and the Scaling Gap focused on concurrency and persistence. We demonstrate that by enforcing a scientific methodology of hypothesize, probe, and code, agents can autonomously write robust, production-grade code skills.