EliteTable: Self-Improving Program Search for Executable Control Policies
On the map: Synthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training also fits: Self-evolving LLM agents
Abstract (arXiv)
EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new proposals, edits of existing solutions, and remixes of several solutions. Performance was evaluated across six Gymnasium control tasks, each with ten generations and fifty candidate slots per generation. Each task was evaluated across ten independently initialized searches. Candidate-score medians rose between the first and final generations in all six tasks, and selected-winner search-score medians rose in five. In CartPole-v1, the selected winner reached the search-score ceiling in the first generation of all ten searches. All ten paired held-out endpoints improved in four of the six tasks. BipedalWalker-v3 and CarRacing-v3 improved without reaching their reporting targets. Six of ten Acrobot-v1 searches declined on held-out episodes, and the median paired change was negative. The results document improvement during program search and the transfer of selected-winner gains to new episodes in some tasks. Comparisons and ablations are needed to establish EliteTable's relative performance and the contributions of its components.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 5 of its 13 references that are in the map. First posted on arXiv 8 Oct 2026.
Builds on
5 of 13 references.
References · 5
- 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
- 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
- 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
- 2018Programmatically Interpretable Reinforcement Learningcited by 193
- 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolutioncited by 174
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026SelfSearch: Reward-Free Search for Self-Improving Agents
- 2025Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?
- 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
- 2026AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
- 2025LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
- 2026Codifying the Judge: Scalable Evaluation via Program Distillation
- 2026LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails
- 2024Mastering Board Games by External and Internal Planning with Language Models