# Towards Self-Evolving Agents: A Human-Inspired Adaptive Exploration-Exploitation Framework for Genetic Network Programming

arXiv: https://arxiv.org/abs/2607.11913 · HTML: https://mlsanity.com/paper/2607.11913/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 66 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

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

- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [EvoFlow: Evolving Diverse Agentic Workflows On The Fly](https://mlsanity.com/paper/2502.07373/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Can Graph Learning Improve Planning in LLM-based Agents?](https://mlsanity.com/paper/2405.19119/) (2024)
- [AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering](https://mlsanity.com/paper/2510.05445/) (2025)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents](https://mlsanity.com/paper/2410.05130/) (2024)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [AgentKit: Structured LLM Reasoning with Dynamic Graphs](https://mlsanity.com/paper/2404.11483/) (2024)
- [Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving](https://mlsanity.com/paper/2511.01633/) (2025)
- [GraphAgent: Agentic Graph Language Assistant](https://mlsanity.com/paper/2412.17029/) (2024)
- [Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning](https://mlsanity.com/paper/2506.03939/) (2025)
- [KnowThyself: An Agentic Assistant for LLM Interpretability](https://mlsanity.com/paper/2511.03878/) (2025)
- [Enhancing Multiagent Genetic Network Programming Performance Using Search Space Reduction](https://mlsanity.com/paper/2412.11146/) (2024)

## Abstract (arXiv)

Recent advancements in agentic AI have increasingly moved toward graph-based methods, driven by the demand for explainable, human-centered, and non-linear reasoning workflows. A prominent example is Genetic Network Programming (GNP), a self-evolving algorithm that utilizes directed graphs to evolve interpretable decision structures for agents. As in most evolutionary algorithms, effectively balancing exploration and exploitation is a key aspect of GNP. However, this trade-off has received limited attention in the GNP literature. To address this gap, we draw inspiration from human developmental patterns, where children prioritize broad experimentation and action over deliberation, with this tendency reversing with age. By mapping transitions between GNP's judgment nodes to deliberation and processing nodes to action, we propose Human-Inspired GNP (HGNP), a novel adaptive framework that dynamically regulates the exploration-exploitation balance throughout the evolutionary process. The method consists of novel adaptive crossover and mutation operators, and a cycle elimination mechanism. HGNP not only improves the evolutionary process but also provides a framework for adjusting the exploration-exploitation balance based on the characteristics of the target environment and its search space. This approach is more effective than tuning via crossover and mutation probabilities in standard GNP. The modifications are general and can be applied to almost all GNP variants. When integrated with standard GNP and two recently introduced GNP variants and evaluated on the Tileworld benchmark, HGNP demonstrated significant performance improvement in agents' strategy. The combination of HGNP with Situation-based GNP (HGNP-SBGNP) achieved the best overall results.