Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval
cs.AI
Submitted: 2026-10-01
Updated: 2026-10-08
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Bio-inspired AI: Integrating Biological Complexity into Artificial Intelligence
- Do Data Valuations Make Good Data Prices?
- SelfEvoSkill: Paired Execution Audits for Skill Revision without External Outcome Supervision
- Don't Let Bandit Feedback Pull Continual LLM-Recommender Updates Off Target
- MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
- MemGPT: Towards LLMs as Operating Systems
- REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents
- When to Forget: A Memory Governance Primitive
- Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
- Handling incomplete outcomes and covariates in cluster-randomized trials: doubly-robust estimation, efficiency considerations, and sensitivity analysis
- A Survey on Data Synthesis and Augmentation for Large Language Models
- Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Memorizing Transformers
- A-MEM: Agentic Memory for LLM Agents
- Fair Document Valuation in LLM Summaries via Shapley Values
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