The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Summary
This paper introduces a taxonomy for Recursive Self-Improvement (RSI) in AI systems, outlining levels L1-L5 and the Headroom-Closed Index to categorize autonomous improvement capabilities.
View Cached Full Text
Cached at: 09/14/26, 02:31 PM
Paper page - The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Source: https://huggingface.co/papers/2609.11873 RSI is the capability of an intelligent system to transform acquired experience and feedback into persistent changes to itself across interaction rounds, such that those changes can affect how later improvements are generated, evaluated, selected, and consolidated. The updated object may be model weights, prompts, code, memory, skills, task distributions, or the improvement mechanism itself. Levels capture autonomy over what is changed, how it is changed, and where later learning experience comes from; they are not paper-quality rankings.
The survey introduces the Headroom-Closed Index (HCI), develops the RSI roadmap represented by the L1-L5 taxonomy, and examines RSI in scientific discovery, embodied intelligence, and software engineering. This repository provides the paper-level, auditable companion to that roadmap.
The 491 baseline papers and 28 table-derived extensions in this collection are retained as RSI-related under the L1-L5 taxonomy. The taxonomy intentionally includes bounded forms and precursors:
L1 - Autonomy over Improvement Execution: the system executes a human-defined improvement procedure, and its accepted results persist into later tasks or rounds.
L2 - Autonomy over Improvement Strategies: the system chooses how to improve a specified target, while the objective, evaluation criterion, or acceptance rule remains external.
L3 - Autonomy over Future Learning Experience: the learner’s evolving state influences the experience, task, or curriculum acquired next.
L4 - Autonomy in Deployment and Environmental Adaptation: reusable memory, skills, or deployed agent components are retained and alter later behavior within a fixed improvement process.
L5 - From Environmental Adaptation to Meta-Improvement: the system improves the mechanism that produces future improvements, such as search, evaluation, or research-control policies. Thus, inclusion does not claim that every entry is a fully autonomous or open-ended RSI system. The L1 and L2 labels make their bounded autonomy explicit.
Similar Articles
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A comprehensive survey of 1,250 papers (2024–2026) on recursive self-improvement in AI, proposing a taxonomy distinguishing bounded self-refinement from open-ended recursive self-improvement, and analyzing the evaluator design space and failure modes.
When AI Builds Itself: Our progress toward recursive self-improvement
Anthropic's Institute publishes analysis on progress toward recursive self-improvement, showing AI is already accelerating AI development—engineers ship 8x more code per quarter—and projecting that AI systems capable of fully autonomous self-improvement could arrive sooner than most institutions are prepared for.
Recursive Criticality of AI Self-Improvement
The paper introduces a model for recursive AI self-improvement, defining a recursive reproduction number to determine when incremental improvements in AI research become self-amplifying or dampening across development cycles.
The Economics of Recursive Self-Improvement [pdf]
This paper examines the economic incentives and dynamics of recursive self-improvement in AI systems, addressing how such processes could scale and their implications for governance and safety.
@SakanaAILabs: From Harness Engineering to RSI How will recursive self-improvement (RSI)—where AI builds and improves itself—be realiz…
Lilian Weng's blog post argues that recursive self-improvement (RSI) in AI will be realized through refining the design and optimization of the 'harness' (the system surrounding the model), and highlights research examples from Sakana AI.