RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Published 16 Sept 2026arXiv:2609.15364
Updated 7 h ago · first seen 14 Sept 2026
paper_01M2J3WSBWK2EPAC5WZV0GG0Y9
Abstract
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.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 5
- Property changedPaperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments: published at changed from 2026-09-15T04:00:00+00:00 to 2026-09-16T04:00:00+00:00
Published15 Sept 2026→16 Sept 2026arxiv - Property changedPaperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv - Property changedPaperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv - Property changedPaperRSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments: published at changed from 2026-09-14T00:00:00+00:00 to 2026-09-15T04:00:00+00:00
Published14 Sept 2026→15 Sept 2026arxiv New paper: RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
huggingface
Sources
Sources 4
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.