What Is This Memory Useful For? Measuring Task-Conditioned Utility in Long-Term Agent Memory
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Learning What to Remember: A Cognitively Grounded Multi-Factor Value Model for Agentic Memory
- Influence Guided Context Selection for Effective Retrieval-Augmented Generation
- EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
- Selective Memory Retention for Long-Horizon LLM Agents
- LLM Agents Already Know When to Call Tools -- Even Without Reasoning
- Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
- SciCode: A Research Coding Benchmark Curated by Scientists
- LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- MeClear: Cooperative Game-Theoretic Attribution and Risk-Aware Memory Clearance for Long-Horizon LLM Agents
- UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
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