Paper page - Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

Source: https://huggingface.co/papers/2610.35193 Authors:

,

,

,

,

,

,

,

,

,

Abstract

This survey defines recursive self-improvement and organizes trustworthy advancement requirements into improvement validity, constraint preservation, and oversight across recursive update stages.

AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prompts, memories, tools, and workflows.Recursive self-improvement(RSI) extends this process toinductive biasesand to the mechanisms that govern future updates, which can themselves be revised and reused across improvement cycles. Yetself-modificationalone does not guarantee trustworthy improvement. Reported gains may reflect flawed evaluations, previously acquired capabilities may deteriorate, and compliance withbehavioral constraintsmay weaken. Compromised artifacts or sensitive information may also persist in successor systems. Changes to improvement mechanisms may invalidate earlier verification results and make human oversight less effective. This survey presents an operational definition and process framework for RSI and organizes the requirements for trustworthy RSI into four interconnected themes: genuine and sustained improvement;behavioral constraints,alignment, andfairness;system securityandprivacy; andtransparencyandcontrollability. We examine these themes from three perspectives:Improvement Validity,Constraint Preservation, andEffective Oversight. This analysis covers improvement diagnosis, proposal generation, proposal evaluation, and update implementation (S1--S4), including the recursive application of these stages to improvement mechanisms (RI). We review risks, safeguards, and evaluation evidence for individual updates, effects inherited by successor systems, and revisions to improvement mechanisms, while distinguishing direct RSI findings from evidence in related systems. Finally, we examine evaluation settings, identify requirements for independent andlongitudinal assessment, and discuss applications and open research problems.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.35193

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.35193 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.35193 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.35193 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.