What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
cs.AI
Submitted: 2026-05-05
Updated: 2026-09-27
Code: https://github.com/langchain-ai/langchain
Terminology
Sources
- ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
- General Agent Evaluation
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- Memory in the Age of AI Agents
- AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
- MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- Scaling sparse feature circuit finding for in-context learning
- Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- Qwen3 Technical Report
- Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
- ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
- AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection