# Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation

arXiv: https://arxiv.org/abs/2603.09987 · HTML: https://mlsanity.com/paper/2603.09987/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 16 of 16)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [MixLLM: Dynamic Routing in Mixed Large Language Models](https://mlsanity.com/paper/2502.18482/) (2025)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities](https://mlsanity.com/paper/2505.06507/) (2025)
- [Evolutionary Large Language Model for Automated Feature Transformation](https://mlsanity.com/paper/2405.16203/) (2024)
- [A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective](https://mlsanity.com/paper/2502.08828/) (2025)
- [Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation](https://mlsanity.com/paper/2505.15152/) (2025)
- [Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming](https://mlsanity.com/paper/2504.21304/) (2025)
- [Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories](https://mlsanity.com/paper/2505.15076/) (2025)
- [Autonomous Data Agents: A New Opportunity for Smart Data](https://mlsanity.com/paper/2509.18710/) (2025)
- [LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation](https://mlsanity.com/paper/2506.09085/) (2025)
- [Distribution Shift Aware Neural Tabular Learning](https://mlsanity.com/paper/2508.19486/) (2025)
- [Learning to Route: A Rule-Driven Agent Framework for Hybrid-Source Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.02388/) (2025)
- [Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation](https://mlsanity.com/paper/2501.10555/) (2025)

## Abstract (arXiv)

Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of feature-operator combinations. Existing solutions rely on discrete search or latent generation, but they are frequently limited by sample inefficiency, invalid candidates, and redundant generations with limited coverage. Large Language Models (LLMs) offer strong priors for producing valid transformations, but current LLM-based FT methods typically rely on static demonstrations, resulting in limited diversity, redundant outputs, and weak alignment with downstream objectives. We propose a framework that optimizes context data for LLM-driven FT by evolving trajectory-level experiences in a closed loop. Starting from high-performing feature transportation sequences explored by reinforcement learning, we construct and continuously update an experience library of downstream task-verified transformation trajectories, and use a diversity-aware selector to form contexts along with a chain-of-thought and guide transformed feature generation toward higher performance. Experiments on diverse tabular benchmarks show that our method outperforms classical and LLM-based baselines and is more stable than one-shot generation. The framework generalizes across API-based and open-source LLMs and remains robust across downstream evaluators.