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
Full article139 words · extracted from huggingface.co · click to collapse
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. RSIAgent coordinates curriculum, actor, and verifier agents to continually explore the environment, validate outcomes, and retain environment-specific knowledge, including reusable causal relationships between actions, conditions, and consequences. It further adopts a broad-then-deep exploration strategy, combining parallel broad recursive self-exploration for discovering diverse environment structures with focused deep self-exploration for uncovering hard cases, hidden constraints, boundary conditions, and previously unknown causal dependencies. The resulting memory is frozen and can be directly reused for downstream tasks without updating model parameters. Experiments on OSWorld-v2 and Agent's Last Exam show that RSIAgent substantially improves strong open-source models, enabling Kimi-K3 and GLM-5.3 to outperform frontier closed-source models including GPT-6.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.15364