T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts

arXiv:2609.12286 · cs.AI, cs.NE · Submitted 2026-09-10 · Read on arXiv

cs.AI, cs.NE

Submitted: 2026-09-10

Updated: 2026-10-14

Code: https://github.com/o-ankomochi-o/T-GADE

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Evolution of Heuristics — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics
• Illuminating search spaces by mapping elites
• Large Language Models as In-context AI Generators for Quality-Diversity
• Determinantal point processes for machine learning
• An Empirical Study of the Non-determinism of ChatGPT in Code Generation
• Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems