Metraipolis › archive › dc_c565bec18bab

MMLA-RSI: Recursive Self-Improvement through RTT and RTMA — arXiv:2610.20294

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20294
License (as archived)
CC0-1.0
Archived
2026-10-15T14:23:49.000Z
SHA-256 of the archived text
1d6dcaf5d68c83a462f2d7e9a0088abe6ac34c6c9e32ae4edefbec0c406e4b13
Stable URL of this page
https://metraipolis.com/documento/dc_c565bec18bab

How to cite

MMLA-RSI: Recursive Self-Improvement through RTT and RTMA — arXiv:2610.20294 — arXiv (en), https://arxiv.org/abs/2610.20294 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c565bec18bab (Metraipolis archive dc_c565bec18bab, sha256 1d6dcaf5d68c83a462f2d7e9a0088abe6ac34c6c9e32ae4edefbec0c406e4b13)
BibTeX
@misc{dcc565bec18bab,
  title = {MMLA-RSI: Recursive Self-Improvement through RTT and RTMA — arXiv:2610.20294},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20294},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c565bec18bab; sha256 1d6dcaf5d68c83a462f2d7e9a0088abe6ac34c6c9e32ae4edefbec0c406e4b13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20294. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains. We propose MMLA-RSI, a recursive self-improvement scheme with two implementations in Memory-Mediated Learning Architecture: Reasoning-Time Training (RTT) changes the policy state $\Phi$, while Reasoning-Time Memory Adaptation (RTMA) changes authoritative memory $M$. Each route also makes its adaptation method an object of improvement. A current numerical updater trains the policy proposing its successor; a current memory manager chooses the records available to the process proposing its successor. An independently admitted successor takes over the same role in the next generation. We give bounded executable rule languages, shared task/proposal interfaces, and one algorithm for either route or their composition. The RTT instance changes scalar schedules in a clipped-momentum update. The RTMA instance chooses NULL or a complete-row write with possible eviction. A fixed interpreter, trusted committer, and independent evaluator bound what can change. State versions, read closures, and conditional properties describe causal execution, accepted transitions, and finite work. Existing numerical-component studies motivate the construction. In four-candidate program selection, retaining LARC feedback updates reduces expected error by 24.65 and 36.65 percentage points for two trained initializations. In chronological continuous-integration replay, feedback binding is positive while retention increases loss. Completed SQL studies improve substantially over an unadapted substrate but do not establish the required additional online benefit. These results characterize their declared components. The two recursive routes and their joint realization are specified here; their beneficial recursive chains and discovery efficiency remain to be evaluated.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20294 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T13:53:35.951Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).