MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves

• URL: http://arxiv.org/abs/2609.06396v2
• Date: Wed, 09 Sep 2026 11:06:36 GMT
• Title: MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
• Abstract summary: Recursive self-improvement lets a system improve the model-building machinery from its own failures, so every later model inherits the gain.<n>Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics.<n>We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable.<n>We present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm.
• Score: 65.60481414910728
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machine-checkable slice, not general capability where questions are open and correctness is settled by argument, replication, or measurement. We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable. To that end we present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm. Data-RSI amplifies existing competence and marks its boundary; Harness-RSI edits a five-slot scaffold without touching weights; Model-RSI internalizes capability into parameters through bounded training. Sharing one loop kernel and artifact vocabulary, they make data, scaffold, and model changes composable rather than exclusive. A two-axis optimizer jointly decides operator order and each operator's proposal policy, while a meta-level policy revises the schedule across terms. We validate MetaRSI-v1 under the field's standard evaluations, on code and closed-form science, with no external teacher: the target model plays every role in its own loop. MetaRSI-v1 reframes self-improvement from a single-surface edit to a composition across the full model-production pipeline, opening two paths: a model route internalizing capability through training, and a harness route leaving weights untouched and thus extending self-improvement to any model reachable through an interface, with Data-RSI redefined as the shared substrate feeding both. The framework further yields refutable laws on where loops exist, how operators compose, and what supervision buys.

Related papers

• Telemetry and Concealment in Self-Adapting Generative AI: Logging Architecture, Adversarial Model Hiding, and the Limits of Detection [0.0]
  Self-adapting generative AI systems render point-in-time validation inadequate.<n>We develop a rigorous telemetry architecture for such models, operating simultaneously in discrete and continuous time.<n>We formalize this as the Model Hiding Problem and provide a systematic taxonomy of six distinct attack strategies against the Part I architecture.
  arXiv  Detail & Related papers  (2026-08-10T03:20:06Z)
• One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement [37.27419953581617]
  Large Language Models (LLMs) often fail to utilize their latent reasoning capabilities.<n>We propose ReQueR, a modular framework that treats reasoning elicitation as an inference-time alignment task.
  arXiv  Detail & Related papers  (2026-04-28T09:52:21Z)
• AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture Search [10.111487060179252]
  This work introduces Ensemble-Decoupled Architecture Search.<n>It predicts system-level performance from single-learner evaluation.<n>It reduces per-candidate search cost from O(M) to O(1) while maintaining O(M) deployment cost only for validated winners.
  arXiv  Detail & Related papers  (2026-03-20T14:57:15Z)
• Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control [82.30868101940068]
  We propose a paradigm in which a model bootstraps its own performance without reliance on external data or teacher models.<n>Our theoretical analysis shows that RSIR acts as a data-driven implicit regularizer, smoothing the optimization landscape.<n>We show that even smaller models benefit, and weak models can generate effective training curricula for stronger ones.
  arXiv  Detail & Related papers  (2026-02-17T15:31:32Z)
• A Generalizable Framework for Building Executable Domain-Specific LLMs under Data Scarcity: Demonstration on Semiconductor TCAD Simulation [20.174394305112198]
  We present a framework for building compact, executable domain-specific LLMs in low-resource settings.<n>We demonstrate the framework by instantiating TcadGPT for semiconductor Technology Computer-Aided Design (TCAD)<n>Using 1.5M synthetic QA pairs and an IR-driven DPO dataset, TcadGPT attains 85.6% semantic accuracy and an 80.0% syntax pass rate on SDE executability tests.
  arXiv  Detail & Related papers  (2026-01-15T07:13:34Z)
• MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval [50.30107119622642]
  Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data.<n>Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge.<n>MarAG-R1 is a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms.
  arXiv  Detail & Related papers  (2025-10-31T15:51:39Z)
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
  Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
  arXiv  Detail & Related papers  (2025-05-15T17:58:33Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Chain-of-Skills: A Configurable Model for Open-domain Question Answering [79.8644260578301]
  The retrieval model is an indispensable component for real-world knowledge-intensive tasks. Recent work focuses on customized methods, limiting the model transferability and scalability. We propose a modular retriever where individual modules correspond to key skills that can be reused across datasets.
  arXiv  Detail & Related papers  (2023-05-04T20:19:39Z)
• Understanding Dynamics of Nonlinear Representation Learning and Its Application [12.697842097171119]
  We study the dynamics of implicit nonlinear representation learning. We show that the data-architecture alignment condition is sufficient for the global convergence. We derive a new training framework, which satisfies the data-architecture alignment condition without assuming it.
  arXiv  Detail & Related papers  (2021-06-28T16:31:30Z)

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.