Microsoft Research

EvoLib: Turning experience into evolving knowledge

LLMs do not get smarter just by remembering more. EvoLib turns experience into evolving knowledge, taking reusable skills and insights that help models learn and adapt across tasks long after deployment.

arXiv Computation and Language
Aug 24

Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents

Tree-of-Experience (ToE) is a hierarchical experience-management framework designed for large language model agents that aligns stored experiences with the agents’ reasoning hierarchy. By organizing experiences into a shared tree of analytical perspectives and reasoning paths, ToE calibrates reliability through environmental outcomes, enabling systematic updating, cross-task transfer, and efficient retrieval. Experiments on Game of 24 and FinEvolveBench demonstrate that ToE yields significant performance gains—31.4% accuracy improvement on Game of 24 and a 41.24% average improvement in tsIC on FinEvolveBench—outperforming both experience-free baselines and conventional experience-management methods.

By Zihao Deng, Yining Zhu, Leiming Wang, Junbo Wang, Jingfei Lu
Microsoft Research
Jul 30

Echoverse: Deep, evolving environments for computer-use agents

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve.

By Akshay Nambi, Yash Pandya, Sahil Gupta, Sarthak Harne, Kavyansh Chourasia, Yash Lara, Ahmed Awadallah, Ece Kamar
arXiv Machine Learning
Jun 4

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

arXiv:2606. 04703v1 Announce Type: cross Abstract: Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs).

By Jingwen Chen, Wenkai Yang, Shengda Fan, Wenbo Nie, Chenxing Sun, Shaodong Zheng, Yangen Hu, Lu Pan, Ke Zeng, Yankai Lin
arXiv AI
Aug 14

MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents

arXiv:2608. 12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions.

By Kaichao Liang, Yuqi Cui, Hao Kong, Xinyuan Huang, Guohaotian Hou, Qingcan Kang, Liang Chen, Yiyang Yin, Ke Ye, Jiaquan Guo, Da Chen, Lingan Zeng, Yixing Peng, Rong Yao, Shixiong Kai, Mingxuan Yuan
arXiv AI
2d ago

From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents

The paper introduces an online skill‑evolution framework that transforms interaction traces and evaluator feedback into a persistent, versioned library of reusable procedures for computer‑use agents. By executing each iteration against a frozen library snapshot, the system updates skills without altering the underlying model parameters. Experiments across four OSWorld domains show that the evolving library consistently outperforms an empty‑library baseline, with gains ranging from 5.7 to 18.6 percentage points, while also revealing domain‑specific temporal stability and challenges in skill retrieval and revision.

By Longtao Hu, Xiao Liang, Linchao Zhu