Self-Evolving Software Agents
For developers of autonomous systems, this work demonstrates a novel approach to enabling genuine software evolution, though results indicate current limits in behavioral inheritance and stability.
This paper introduces self-evolving software agents that combine BDI reasoning with LLMs to autonomously evolve goals, reasoning, and executable code. In a dynamic multi-agent environment, agents autonomously discovered new goals and generated executable behaviors from minimal prior knowledge.
Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software agents, combining BDI reasoning with LLMs to enable autonomous evolution of goals, reasoning, and executable code. We propose a BDI-LLM architecture in which an automated evolution module operates alongside the agent's reasoning loop, eliciting new requirements from experience and synthesizing corresponding design and code updates. A prototype evaluated in a dynamic multi-agent environment shows that agents can autonomously discover new goals and generate executable behaviours from minimal prior knowledge. The results indicate both the feasibility and current limits of LLM-driven evolution, particularly in terms of behavioural inheritance and stability.