AlgoEvolve: LLM-driven Meta-evolution of Algorithmic Trading Programs
Quick Answer
AlgoEvolve leverages Large Language Models to evolve algorithmic trading strategies, demonstrating superior performance over human-designed methods.
Quick Take
The framework adapts trading rules autonomously and utilizes a meta-evolutionary approach to enhance prompt generation, significantly reducing zero-trade failures.
Key Points
- AlgoEvolve generates and iteratively improves executable trading strategies using .
- The system shows emergent regime-adaptive logic with autonomous trading rule shifts.
- A meta-evolutionary outer loop enhances search heuristics for program synthesis.
- Heuristics balance exploration and exploitation, outperforming initial human designs.
- Results indicate LLM-based evolution is viable for complex program synthesis.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and proofs. Most current applications focus on static coding benchmarks. We extend this paradigm to algorithmic trading. This domain is uniquely challenging because it is noisy, non-stationary, and highly discontinuous. We present AlgoEvolve, an LLM-driven evolutionary framework that generates, evaluates, and iteratively improves executable trading strategies. These strategies are expressed as Python code and evaluated through a rigorous testing protocol. Across multiple experiments, the system exhibits emergent regime-adaptive strategy logic, including autonomous shifts in trading rules. We further introduce a meta-evolutionary outer loop that evolves the prompts guiding program synthesis in the inner loop. This outer loop discovers improved search heuristics. These heuristics balance exploration and exploitation while reducing zero-trade failures. They consistently outperform initial human-designed instructions. The results demonstrate that LLM-based semantic evolution provides a viable approach for continual program synthesis in complex environments.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.26173 [cs.AI] |
| (or arXiv:2606.26173v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26173 arXiv-issued DOI via DataCite |
Submission history
From: Gautam Shroff [view email]
[v1]
Wed, 24 Jun 2026 10:05:03 UTC (679 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.