# Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments

arXiv: https://arxiv.org/abs/2610.18427 · HTML: https://mlsanity.com/paper/2610.18427/

## 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 25 of its 39 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [Data Banzhaf: A Robust Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2205.15466/) (2022)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [In-context Example Selection with Influences](https://mlsanity.com/paper/2302.11042/) (2023)
- [Data Curation Alone Can Stabilize In-context Learning](https://mlsanity.com/paper/2212.10378/) (2022)
- [Recursive Self-Evolving Agents via Held-Out Selection](https://mlsanity.com/paper/2606.28374/) (2026)
- [Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents](https://mlsanity.com/paper/2607.24300/) (2026)
- [What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills](https://mlsanity.com/paper/2608.04562/) (2026)
- [Coalition-Aware Skill Reliability for Self-Evolving Agents](https://mlsanity.com/paper/2608.22610/) (2026)
- [SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents](https://mlsanity.com/paper/2608.13173/) (2026)
- [Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner](https://mlsanity.com/paper/2608.23268/) (2026)

## Abstract (arXiv)

Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining. Systems such as ACE and Dynamic Cheatsheet keep it as a playbook: lessons the agent writes after each task and reads in its prompt. A key challenge is to decide which lessons improve later tasks. Current systems leave the decision to the agent itself, which makes performance unstable: the same procedure can write a playbook that helps or one that falls up to 69.6 points below no playbook. These findings motivate valuing lessons by their measured effect on task success rather than by the agent's judgment. We propose Randomized Block Curation (RBC), which measures this effect with a randomized experiment on practice tasks. It groups related lessons into blocks large enough to move success measurably and, on each practice task, includes or leaves out every block at random. Random inclusion makes tasks with and without a block comparable, so the gap in their success estimates the block's effect. RBC keeps the blocks that help and, since the same procedure can write a helpful or a harmful playbook, grows several and serves whichever curated, whole or no playbook scores best on fresh practice episodes. Across two memory systems, three models and three benchmarks, RBC raises average success to 66.9, against 55.5 with the whole playbook, 54.1 with no playbook and 53.8 when the agent's own judgment picks the lessons to keep.