RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

arXiv:2609.15364 · cs.AI, cs.CL, cs.CV · Submitted 2026-09-14 · Read on arXiv

cs.AI, cs.CL, cs.CV

Submitted: 2026-09-14

Updated: 2026-09-18

Comments: 49 pages

Code: https://github.com/AetherLabsAI/RSIAgent

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Actor — 92× in this paper · explained in 3 episodes
• Verifier — 71× in this paper · explained in 2 episodes
• Verification — 26× in this paper · explained in 2 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Deep Recursive Self-exploration — 18× in this paper
• Broad Recursive Self-exploration — 17× in this paper
• Trace — 7× in this paper · explained in 2 episodes
• Downstream Tasks — 6× in this paper · explained in 2 episodes
• Multi-Agent Framework — 6× in this paper · explained in 3 episodes
• Adaptation — 5× in this paper · explained in 1 episode
• Agent Harness — 5× in this paper · explained in 1 episode
• Distillation — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Failure Modes — 4× in this paper · explained in 3 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper · explained in 1 episode
• Agent Skills — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Causal Discovery — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Multi-Agent System — 2× in this paper · explained in 5 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Quantifying Uncertainty — 1× in this paper · explained in 5 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
• Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
• Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce
• VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
• GUI Agents for Continual Game Generation
• ZhuLong: Execution-Grounded LLM Agent for EDA Scripting with Offline API Self-Exploration
• AREX: Towards a Recursively Self-Improving Agent for Deep Research
• GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
• RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
• Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
• A Self-Improving Coding Agent
• Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
• Agents' Last Exam
• Cradle: Empowering Foundation Agents Towards General Computer Control
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection