Position: Agentic Evolution is the Path to Evolving LLMs
cs.AI
Submitted: 2026-01-30
Updated: 2026-11-04
Code: https://github.com/A-EVO-Lab/a-evolve
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Titans: Learning to Memorize at Test Time
- It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization
- Training-Free Group Relative Policy Optimization
- Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- Retrieval-Augmented Generation with Graphs (GraphRAG)
- Test-Time Learning for Large Language Models
- R-Zero: Self-Evolving Reasoning LLM from Zero Data
- SelfEvolve: A Code Evolution Framework via Large Language Models
- Scaling Laws for Neural Language Models
- Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- OpenAI o1 System Card
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
- Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
- OpenAI GPT-5 System Card
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents