Agent Plasticity: Measuring Self-Improvement Through Experience
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- Metacognitive Reuse: Turning Recurring LLM Reasoning Into Concise Behaviors
- When Does Continual Learning Require Learning
- How Many Instructions Can LLMs Follow at Once?
- Meta-Harness: End-to-End Optimization of Model Harnesses
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
- MemGPT: Towards LLMs as Operating Systems
- A Self-Improving Coding Agent
- AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
- Recursive Language Models
- MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
- LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
Related papers
- 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
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems