Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
cs.AI, cs.MA
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/yukyeongleee/wikitrace
Project page: https://pi.dev
Terminology
Sources
- Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
- PREPING: Zero-Task Agent Memory Construction via Self-Practice
- Organize then Retrieve: Hierarchical Memory Navigation for Efficient Agents
- When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
- Memory in the Age of AI Agents
- Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
- How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- Useful Memories Become Faulty When Continuously Updated by LLMs
- Rethinking Experience Utilization in Self-Evolving Language Model Agents
- Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
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