
Self-Improvement Memory Enables Continual Recursive Self-Improvement
18/11/2026
0:00
NaN:NaN:NaN
This episode examines a November 2026 paper on continual recursive self-improvement, where an LLM-driven optimizer keeps improving an agent's harness (the code around a frozen model) after the benchmark or the underlying model changes. It starts from a striking result: a harness evolved with one model scored about five and a half points below the plain seed harness when moved to a different model. The cause is that the optimizer inherits the evolved code without the reasons behind each edit, much like a legacy codebase with no commit history. The proposed fix, Self-Improvement Memory, logs each edit's root cause, rationale, predicted outcome, observed outcome and provenance. It is compared against cold start, harness transfer and problem-only memory conditions. The discussion also relates the idea to Reflexion and to continual learning, and it notes that most of the evidence comes from single optimization runs, which is a reason to treat the headline gains cautiously.
Sources:
1. Self-Improvement Memory Enables Continual Recursive Self-Improvement — Xin Yu, Fei Xia, Jiaqi Pan, Youbao Tang, Chengzhi Liu, Adams Yu, Sicong Jiang, Yanfei Chen, Lingzhou Xue, Ting Yu, 2026
http://arxiv.org/abs/2611.18856
2. Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents — Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, Jeff Clune, 2025
https://scholar.google.com/scholar?q=Darwin+G%C3%B6del+Machine%3A+Open-Ended+Evolution+of+Self-Improving+Agents
3. Automated Design of Agentic Systems (ADAS) — Shengran Hu, Cong Lu, Jeff Clune, 2024
https://scholar.google.com/scholar?q=Automated+Design+of+Agentic+Systems+%28ADAS%29
4. Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation — Eric Zelikman, Eliana Lorch, Lester Mackey, Adam Tauman Kalai, 2023
https://scholar.google.com/scholar?q=Self-Taught+Optimizer+%28STOP%29%3A+Recursively+Self-Improving+Code+Generation
5. A Comprehensive Survey of Continual Learning: Theory, Method and Application — Liyuan Wang, Xingxing Zhang, Hang Su, Jun Zhu, 2023
https://scholar.google.com/scholar?q=A+Comprehensive+Survey+of+Continual+Learning%3A+Theory%2C+Method+and+Application
6. Reflexion: Language Agents with Verbal Reinforcement Learning — Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao, 2023
https://scholar.google.com/scholar?q=Reflexion%3A+Language+Agents+with+Verbal+Reinforcement+Learning
7. Voyager: An Open-Ended Embodied Agent with Large Language Models — Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Linxi Fan, Anima Anandkumar and colleagues, 2023
https://scholar.google.com/scholar?q=Voyager%3A+An+Open-Ended+Embodied+Agent+with+Large+Language+Models
8. Agent Workflow Memory — Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig, 2024
https://scholar.google.com/scholar?q=Agent+Workflow+Memory
9. A Survey on the Memory Mechanism of Large Language Model based Agents — Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen and colleagues, 2024
https://scholar.google.com/scholar?q=A+Survey+on+the+Memory+Mechanism+of+Large+Language+Model+based+Agents
10. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models (ACE) — Zhang, Hu, Upasani, Ma et al., 2026
https://scholar.google.com/scholar?q=Agentic+Context+Engineering%3A+Evolving+Contexts+for+Self-Improving+Language+Models+%28ACE%29
11. GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning — Agrawal, Tan, Soylu et al., 2026
https://scholar.google.com/scholar?q=GEPA%3A+Reflective+Prompt+Evolution+Can+Outperform+Reinforcement+Learning
12. Meta-Harness: End-to-End Optimization of Model Harnesses — Lee, Nair, Zhang, Lee et al., 2026
https://scholar.google.com/scholar?q=Meta-Harness%3A+End-to-End+Optimization+of+Model+Harnesses
13. RRSI: Regularized Recursive Self-Improvement of Agent Harnesses — Xia, Han, Wang, Chen et al., 2026
https://scholar.google.com/scholar?q=RRSI%3A+Regularized+Recursive+Self-Improvement+of+Agent+Harnesses
14. Are Self-Evolving Agents Continual Learners? — Chen, Huang, Xu, Zhao, McQuinn, Liu, Yao, 2026
https://scholar.google.com/scholar?q=Are+Self-Evolving+Agents+Continual+Learners%3F
15. HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution — Luo, Xue, Wang, Hu, Deng, 2026
https://scholar.google.com/scholar?q=HarnessBank%3A+Semantic+Gene-Bank+Search+with+Gated+Verification+for+Agent-Harness+Self-Evolution
16. Harness2: Recursive Agent Harnessing for an Open World — Xu, Chen, CuiZhu, Mishra et al., 2026
https://scholar.google.com/scholar?q=Harness2%3A+Recursive+Agent+Harnessing+for+an+Open+World
17. ExpeL: LLM Agents Are Experiential Learners — Zhao, Huang, Xu, Lin, Liu, Huang, 2024
https://scholar.google.com/scholar?q=ExpeL%3A+LLM+Agents+Are+Experiential+Learners
18. Rethinking the Evaluation of Harness Evolution for Agents — Wang, Zhu, Hu, Yuan et al., 2026
https://scholar.google.com/scholar?q=Rethinking+the+Evaluation+of+Harness+Evolution+for+Agents
19. Overcoming catastrophic forgetting in neural networks (EWC) — Kirkpatrick et al., 2017
https://scholar.google.com/scholar?q=Overcoming+catastrophic+forgetting+in+neural+networks+%28EWC%29
Interactive Visualization: Self-Improvement Memory Enables Continual Recursive Self-Improvement
Otros episodios de "AI Post Transformers"



No te pierdas ningún episodio de “AI Post Transformers”. Síguelo en la aplicación gratuita de GetPodcast.








