The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

• URL: http://arxiv.org/abs/2609.11873v2
• Date: Tue, 15 Sep 2026 08:48:28 GMT
• Title: The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
• Abstract summary: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement.
• Score: 66.06470438483697
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution autonomy, improvement-strategy autonomy, experience-acquisition autonomy, and environment-adaptation autonomy, to recursive meta-improvement. Next we examine RSI across scenarios (e.g., scientific discovery, embodied intelligence, software engineering), highlighting their distinct requirements and development speeds. Drawing on diverse industry practices and preliminary empirical evidence, we connect RSI research with practical systems and identify key challenges to achieving genuine RSI.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction [40.686692342584884]
  RoboCortex is a self-evolving framework that enables robots to autonomously induce navigations and cognitive strategies.<n>Our core innovation is an Autonomous Knowledge Induction mechanism that distills multimodal trajectories into a structured Navigation Heuristic Library.<n>We show that RoboCortex consistently outperforms strong baselines in both task success and exploration efficiency.
  arXiv  Detail & Related papers  (2026-05-18T17:52:14Z)
• Let the Barbarians In: How AI Can Accelerate Systems Performance Research [80.43506848683633]
  We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems.<n>We demonstrate that ADRS-generated solutions can match or even outperform human state-of-the-art designs.
  arXiv  Detail & Related papers  (2025-12-16T18:51:23Z)
• SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents [58.174206358223415]
  Self-Evolving Embodied Agents-R1, or SEEA-R1, is the first reinforcement fine-tuning framework designed for self-evolving embodied agents.<n>We show that SEEA-R1 can support autonomous adaptation and reward-driven self-evolution.
  arXiv  Detail & Related papers  (2025-06-26T18:00:07Z)
• Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects [13.655659915158633]
  Chain-of-Thought (CoT) reasoning is an advanced cognitive method that simulates human thinking processes.<n>This paper investigates how CoT methods improve the reasoning abilities of autonomous driving models.
  arXiv  Detail & Related papers  (2025-05-26T17:06:00Z)
• Foundation Models for Autonomous Driving System: An Initial Roadmap [17.198146951189635]
  Recent advancements in Foundation Models (FMs) have significantly enhanced Autonomous Driving Systems (ADSs)<n>ADSs are highly complex cyber-physical systems that demand rigorous software engineering practices to ensure reliability and safety.<n>We present a structured roadmap for integrating FMs into autonomous driving, covering three key aspects: the infrastructure of FMs, their application in autonomous driving systems, and their current applications in practice.
  arXiv  Detail & Related papers  (2025-04-01T15:45:31Z)
• Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models [75.4890331763196]
  Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems.<n>LLM-based Agentic RS (LLM-ARS) can offer more interactive, context-aware, and proactive recommendations.
  arXiv  Detail & Related papers  (2025-03-20T22:37:15Z)
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
  Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
  arXiv  Detail & Related papers  (2025-02-20T13:50:02Z)
• Evolutionary Reinforcement Learning: A Systematic Review and Future Directions [18.631418642768132]
  Evolutionary Reinforcement Learning (EvoRL) is a solution to the limitations of reinforcement learning and evolutionary algorithms (EAs) in complex problem-solving. EvoRL integrates EAs and reinforcement learning, presenting a promising avenue for training intelligent agents. This systematic review provides insights into the current state of EvoRL and offers a guide for advancing its capabilities in the ever-evolving landscape of artificial intelligence.
  arXiv  Detail & Related papers  (2024-02-20T02:07:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.