Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Localizing Factual Inconsistencies in Attributable Text Generation
- HaluMem: Evaluating Hallucinations in Memory Systems of Agents
- MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
- Evaluating Factuality in Generation with Dependency-level Entailment
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Eywa: Provenance-Grounded Long-Term Memory for AI Agents
- VISTA: Verification In Sequential Turn-based Assessment
- SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
- ChatGPT as a Factual Inconsistency Evaluator for Text Summarization
- On Faithfulness and Factuality in Abstractive Summarization
- FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation
- Generative Agents: Interactive Simulacra of Human Behavior
- FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations
- Reflexion: Language Agents with Verbal Reinforcement Learning
- A-MEM: Agentic Memory for LLM Agents
- ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control
- A Survey on the Memory Mechanism of Large Language Model based Agents
- ExpeL: LLM Agents Are Experiential Learners
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