RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
- Published
- Source
- arXiv
- Paper number
- 1086
- Field
- AI / General
- arXiv ID
- 2609.15364
Key points
- The paper proposes a recursive self-improvement loop that rotates three agent roles—curriculum, execution, and verification—to accumulate environment knowledge without human supervision.
- A two-stage strategy of broad parallel exploration followed by deep digging on important directions captures corner cases and hidden constraints into memory.
- Instead of logging simple successes, it stores action-condition-outcome causal relations in memory and reuses them on other tasks.
- Using memory alone, with no training or parameter updates, it lifted open-source models (Kimi-K3, GLM-5.3) to or above GPT-6-class performance.
- It demonstrated passing frontier closed models with an OSWorld-v2 partial score of 78.82 and 71.60 on Agent's Last Exam.
Paper links
External research summaries. These are not HDATF publications or measured product results.