# From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory

arXiv: https://arxiv.org/abs/2610.04868 · HTML: https://mlsanity.com/paper/2610.04868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [Memp: Exploring Agent Procedural Memory](https://mlsanity.com/paper/2508.06433/) (2025)
- [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://mlsanity.com/paper/2512.10696/) (2025)
- [Mem-α: Learning Memory Construction via Reinforcement Learning](https://mlsanity.com/paper/2509.25911/) (2025)
- [How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models](https://mlsanity.com/paper/2510.02453/) (2025)
- [Meta-RL Induces Exploration in Language Agents](https://mlsanity.com/paper/2512.16848/) (2025)
- [SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses](https://mlsanity.com/paper/2604.03088/) (2026)
- [AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation](https://mlsanity.com/paper/2601.08323/) (2026)
- [Enhancing Web Agents with a Hierarchical Memory Tree](https://mlsanity.com/paper/2603.07024/) (2026)
- [Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs](https://mlsanity.com/paper/2602.02556/) (2026)
- [MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs](https://mlsanity.com/paper/2605.08374/) (2026)
- [SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces](https://mlsanity.com/paper/2605.15215/) (2026)
- [EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses](https://mlsanity.com/paper/2609.39284/) (2026)

## Abstract (arXiv)

Memory-augmented agents typically integrate procedural knowledge by injecting retrieved skills directly into text prompts. This approach dangerously equates readable text with reliable execution. To bridge this gap, we introduce From Memory to Guide, a novel paradigm that transitions procedural memory from passive text delivery to active, inference-time policy adaptation. We instantiate this paradigm through the Spatio-Temporal Composer, an active policy compiler that explicitly manages exactly how and when retrieved knowledge should be applied. Rather than treating skills as plug-and-play modules, Composer dynamically aligns historical knowledge with current environmental constraints (spatial adaptation) and precisely dictates its applicable lifecycle (temporal orchestration). It actively transforms static memories into strictly bounded Runtime Guides---equipping the agent with localized objectives and behavioral guardrails without requiring a single parameter update. Extensive evaluations on 13 demanding, long-horizon software engineering tasks in EngramBench demonstrate the clear advantages of this architecture. Composer not only robustly prevents context mismatch but drives an absolute pass-rate increase of 7.2 percentage points on the most complex tasks, while simultaneously slashing the main agent's token usage by 32.2%.