Towards AGI A Pragmatic Approach Towards Self Evolving Agent
Indrajit Kar, Sammy Zonunpuia, Zonunfeli Ralte

TL;DR
This paper proposes a hierarchical self-evolving multi-agent framework that enables LLM-based agents to autonomously adapt, generate tools, and evolve their reasoning capabilities through various learning paradigms, demonstrating improved performance on complex tasks.
Contribution
It introduces a novel multi-agent architecture with integrated evolution mechanisms, allowing LLM agents to self-improve and adapt continuously, which is a significant advancement over static models.
Findings
Evolved agents outperform original agents across tasks.
Curriculum Learning enables fast recovery and strong generalization.
Genetic Algorithms increase behavioral diversity.
Abstract
Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment, lacking the ability to autonomously expand capabilities, generate new tools, or evolve their reasoning. This work introduces a hierarchical self-evolving multi-agent framework that integrates a Base LLM, an operational SLM agent, a Code-Generation LLM, and a Teacher-LLM to enable continuous adaptation. The workflow begins with the agent attempting a task using reasoning and existing tools; if unsuccessful, it escalates to tool synthesis through the Code-Gen LLM, and when failures persist, it triggers an evolution phase using Curriculum Learning (CL), Reward-Based Learning (RL), or Genetic Algorithm (GA) evolution. Using the TaskCraft dataset rich in hierarchical tasks, tool-use traces, and difficulty scaling we evaluate these paradigms. CL delivers fast recovery and strong generalization, RL…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Multimodal Machine Learning Applications · Domain Adaptation and Few-Shot Learning
