RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent, a training-free multi-agent framework, builds reusable environment memory enabling Kimi-K3 and GLM-5.3 to beat GPT-6.
RSIAgent is a training-free framework for recursive self-improvement through autonomous memory construction, coordinating curriculum, actor, and verifier agents. It uses broad-then-deep exploration to capture environment structures, hidden constraints, and causal dependencies, and freezes the resulting memory for direct reuse without parameter updates. On OSWorld-v2 and Agent's Last Exam it substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.
- Training-free multi-agent framework with curriculum, actor, verifier roles
- Frozen environment memory reusable across tasks without parameter updates
- Enables Kimi-K3 and GLM-5.3 to outperform GPT-6 on agent benchmarks
- Evaluated on OSWorld-v2 and Agent's Last Exam
From the original article
1 min read at huggingface.co
Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce RSIAgent, a training-free multi-agent framework for recursive self-improvement through autonomous memory construction.
By Sibo Zhu, Shicheng Fan, Xinyue Wang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.