paper-with-me

Papers

Synthesizing Procedural Memory: Challenges and Architectures in Automated Workflow Generation

2025-12-23 · Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj 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.

📄 PDF Abstract BibTeX arXiv:2512.20278

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data

2026-04-22 · Fengxian Dong, Zhi Zheng, Xiao Han, Wei Chen 외 arxiv

Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditional methods rely on predefined operator li…

An Analysis and Comparison of ACT-R and Soar

2022-01-23 · John E. Laird

This is a detailed analysis and comparison of the ACT-R and Soar cognitive architectures, including their overall structure, their representations of agent data and metadata, and their associated processing. It focuses o…

Decision Making

MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents

2026-05-07 · Ashwani Anand, Ivi Chatzi, Ritam Raha, Anne-Kathrin Schmuck arxiv

Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agents comply with the rules from these manual…

Simulating Action Dynamics with Neural Process Networks

2017-11-14 · ICLR 2018 1 · Antoine Bosselut, Omer Levy, Ari Holtzman, Corin Ennis 외

Understanding procedural language requires anticipating the causal effects of actions, even when they are not explicitly stated. In this work, we introduce Neural Process Networks to understand procedural text through (n…

Memp: Exploring Agent Procedural Memory

2025-08-08 · Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu 외 arxiv

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to e…