From Model Inspection to Executable Learning Rules: A Survey of LLM-Driven Algorithm Synthesis and Validation

Learning systems run on rules that are fixed before they start: an optimizer and its schedule, an aggregation formula in federated learning, a detector for a monitored plant. Large language models (LLMs) that can read numerical state and write code now make it possible to inspect a process while it runs and to replace such a rule with a program written for that process. This survey examines that possibility along a five-stage loop of observation, agentic reasoning, program synthesis, verification and deployment. Methods are compared on four axes that cut across applications: the knowledge available to the LLM, the artifact it generates or modifies, the mechanism that validates it, and the cost and risk of using it. Three systems anchor the analysis: GradReason, which replaces training epochs with training-data-free weight updates; FedReason, which writes aggregation programs after reading client models; and PIA, which composes physical residual detectors for cyber-physical systems. They are read beside reactive optimizers, LLM-guided program search, learned optimizers, and non-agentic forms of knowledge reuse such as model annealing and knowledge fermentation. In the reported ablations, removing cheap empirical feedback costs far more than withholding model internals or documentation; agents mostly select and tune techniques that were known before their training cut-off; and once a working update is found, a fixed rule can recover most of the gain without inference cost. We derive a break-even condition for agent latency, propose a minimum evaluation protocol with budget-matched and rule-encoding controls, and set out open problems in discovery beyond prior knowledge, acceptance rules with long horizons, and synthesis under adversaries.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24234920
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

From Model Inspection to Executable Learning Rules: A Survey of LLM-Driven Algorithm Synthesis and Validation

Ali Mohammadi Ruzbahani, Abouzadeh Rezvan
Zenodo (CERN European Organization for Nuclear Research)
Privacy-Preserving Technologies in Data
article

From Model Inspection to Executable Learning Rules: A Survey of LLM-Driven Algorithm Synthesis and Validation

Ali Mohammadi Ruzbahani, Abouzadeh Rezvan
article en

Abstract

Learning systems run on rules that are fixed before they start: an optimizer and its schedule, an aggregation formula in federated learning, a detector for a monitored plant. Large language models (LLMs) that can read numerical state and write code now make it possible to inspect a process while it runs and to replace such a rule with a program written for that process. This survey examines that possibility along a five-stage loop of observation, agentic reasoning, program synthesis, verification and deployment. Methods are compared on four axes that cut across applications: the knowledge available to the LLM, the artifact it generates or modifies, the mechanism that validates it, and the cost and risk of using it. Three systems anchor the analysis: GradReason, which replaces training epochs with training-data-free weight updates; FedReason, which writes aggregation programs after reading client models; and PIA, which composes physical residual detectors for cyber-physical systems. They are read beside reactive optimizers, LLM-guided program search, learned optimizers, and non-agentic forms of knowledge reuse such as model annealing and knowledge fermentation. In the reported ablations, removing cheap empirical feedback costs far more than withholding model internals or documentation; agents mostly select and tune techniques that were known before their training cut-off; and once a working update is found, a fixed rule can recover most of the gain without inference cost. We derive a break-even condition for agent latency, propose a minimum evaluation protocol with budget-matched and rule-encoding controls, and set out open problems in discovery beyond prior knowledge, acceptance rules with long horizons, and synthesis under adversaries.

Zenodo (CERN European Organization for Nuclear Research)
University of Calgary (CA)
Privacy-Preserving Technologies in Data
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon