Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction
cs.AI, cs.LG
Submitted: 2026-10-03
Updated: 2026-10-03
Terminology
Sources
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
- AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
- MemGPT: Towards LLMs as Operating Systems
- Qwen2.5 Technical Report
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
- ReAct: Synergizing Reasoning and Acting in Language Models
- CoEvo-Mem: Co-Evolving Retrieval Policy and Memory Bank for LLM Agents
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
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