RoutePrism: Tracing Construction Order Effects in Agent Memory
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/vectorize-io/agent-memory-benchmark
Terminology
Sources
- Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
- MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
- Selection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrieval
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
- AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
- EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
- Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents
- Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
- MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
- Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation
- MemGPT: Towards LLMs as Operating Systems
- Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents
- When Not to Write Memory: Governing False Promotion from Correlated Agent Traces
- Reliable Post-Retrieval Assembly for Agent Memory: Separating Evidence Extraction from Policy Execution
- From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
- Compiled Memory: Not More Information, but More Precise Instructions for Language Agents
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