#procedural-memory News & Analysis

4 articles tagged with #procedural-memory. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Jun 237/10

🧠

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation

Researchers introduce AFTER, a benchmark evaluating how procedural memory in large language models transfers across tasks, roles, and model types. Testing on 382 enterprise tasks across six professional roles, the study finds that procedural memory improves performance by 3.7-6.7 points per refinement round, with multi-model trained skills achieving 73.1% cross-model accuracy—though some skills generalize broadly while others become role-specific.

AIBullisharXiv – CS AI · Jun 97/10

🧠

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

SKILL.nb is a new framework that improves AI agent reliability by selectively formalizing workflow steps based on execution evidence, storing them as versioned notebooks with natural language guidance and executable code. The system achieved 53.7% success on web automation tasks and retained 91.7% performance across multiple re-executions, significantly outperforming existing baselines in handling environment drift and task specification changes.

AIBullisharXiv – CS AI · May 297/10

🧠

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models

Researchers introduce VLA-Pro, a framework that enhances vision-language-action models for robotics by storing and retrieving task-specific procedural memories during inference. The approach achieves dramatic performance gains—up to 207% improvement in simulation and raising real-world success rates from 5.8% to 65%—demonstrating significant progress in cross-task generalization for robotic manipulation.

AINeutralarXiv – CS AI · Jun 86/10

🧠

AdMem: Advanced Memory for Task-solving Agents

Researchers introduce AdMem, a unified memory framework that enables large language model agents to effectively store, organize, and retrieve semantic, episodic, and procedural knowledge across long-horizon tasks. The system uses a multi-agent architecture with reward-based evaluation to automatically generate and manage memories, demonstrating improved robustness compared to existing approaches.