Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory
cs.AI
Submitted: 2026-09-24
Updated: 2026-09-24
Terminology
Sources
- Memory Reward Inflation in Self-Improving LLM Agents
- Collapse of Self-trained Language Models
- Large Language Models Cannot Self-Correct Reasoning Yet
- The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
- Mendel G\"odel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
- Self-Refine: Iterative Refinement with Self-Feedback
- Spontaneous Reward Hacking in Iterative Self-Refinement
- Can Large Reasoning Models Self-Train?
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
- Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
- Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
- Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
- G\"odel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
- Self-Rewarding Language Models
- STaR: Bootstrapping Reasoning With Reasoning
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection