📰 Articles

🧩 Context Engineering & Harness Engineering

• Why Character.AI Forgets You — And What Persistent Memory Actually Requires
• 221 Agents: Multi-Agent Coordination Lessons
• OpenClaw Multi-Tenancy: Why VM-Per-User Does Not Scale
• Survey of AI Agent Memory Frameworks
• Memory in Language Model-Enabled Agents
• Mastering LLM Memory: A Comprehensive Guide
• LLM Powered Autonomous Agents
• Harness Engineering for Self-Improvement
• Why Character.AI Forgets You — And What Persistent Memory Actually Requires
• 221 Agents: Multi-Agent Coordination Lessons
• OpenClaw Multi-Tenancy: Why VM-Per-User Does Not Scale

📏 Benchmarks

🎮 Dynamic Benchmarks & Simulation Environments

• Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
• [code
• [data
• [proj
• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
• [code
• [proj
• StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
• MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
• [code
• [data
• ARE: Scaling Up Agent Environments and Evaluations
• [code
• AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
• [code
• SEAGym: An Evaluation Environment for Self-Evolving LLM Agents
• [code
• [code
• agent-memory-bench
• [code
• [data

🎬 Multimodal Benchmarks

• MBench: A Comprehensive Benchmark on Memory Capability for Video World Models
• [code
• [proj
• [leaderboard
• RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
• [code
• [data
• [proj
• [leaderboard
• DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
• [code
• [data
• [leaderboard
• Persona-MME: A Benchmark for Long-Term Personalized Multimodal LLMs
• [code
• [data
• TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
• [code
• [data
• [proj
• LVBench: An Extreme Long Video Understanding Benchmark
• [code
• Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
• [code
• MovieChat+: Question-aware Sparse Memory for Long Video Question Answering
• [code
• CinePile: A Long Video Question Answering Dataset and Benchmark
• [code
• LongVideoBench: A Benchmark for Long-Context Interleaved Video-Language Understanding
• [code
• EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
• [code
• LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design
• [code
• [proj
• According to Me: Long-Term Personalized Referential Memory QA (ATM-Bench)
• [code
• [data
• [proj
• [leaderboard

💬 Plain-Text Benchmarks

• Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
• [code
• [code
• Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
• [code
• [data
• MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
• [code
• [data
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
• [code
• [data11
• [data2
• Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
• [code
• [data
• LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
• [code
• [data
• NoLiMa: Long-Context Evaluation Beyond Literal Matching
• [code
• [data
• [code
• [data
• LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
• [code
• Minerva: A Programmable Memory Test Benchmark for Language Models
• [code
• MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
• [code
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
• OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
• LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
• [data
• Evaluating Very Long-Term Conversational Memory of LLM Agents
• [code
• [data
• ∞Bench: Extending Long Context Evaluation Beyond 100K Tokens
• [code
• LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
• StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
• [code
• Are We Ready For An Agent-Native Memory System?
• [code
• [code
• [code
• Agent Memory Leaderboard
• [code
• Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models
• [code
• [data11
• [data2
• HaluMem: Evaluating Hallucinations in Memory Systems of Agents
• Agent Memory Benchmark (AMB)
• [code

🔒 Memory Security & Defense

🧩 Context Engineering & Harness Engineering

• Agent Memory Guard
• [code
• [pypi
• From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
• mnemo poisoning probes
• [attack
• [defense
• [pypi
• inspeximus (formerly mnemo) poisoning probes
• [attack
• [defense

📈 Papers - Memory for Agent Evolution

🧩 Context Engineering & Harness Engineering

• Code as Agent Harness
• [code
• SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
• [code
• LCM: Lossless Context Management
• [code
• CL-bench: A Benchmark for Context Learning
• [code
• Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
• M\*: Every Task Deserves Its Own Memory Harness
• Everything is Context: Agentic File System Abstraction for Context Engineering
• [code
• AgentFold: Long-Horizon Web Agents with Proactive Context Management
• [code
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• [code
• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• Self-Harness: Harnesses That Improve Themselves
• [code
• Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
• [code
• TokenPilot: Cache-Efficient Context Management for LLM Agents
• [code

🧭 Reinforcement Learning & Continual Learning

• MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
• [code
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• [code
• Learning, Fast and Slow: Towards LLMs That Adapt Continually
• [code
• [blog
• CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
• [code
• Memory Intelligence Agent
• [code
• PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
• [code
• Toward Autonomous Long-Horizon Engineering for ML Research
• [code
• OpenClaw-RL: Train Any Agent Simply by Talking
• [code
• Memento-Skills: Let Agents Design Agents
• [code
• Memento 2: Learning by Stateful Reflective Memory
• [code
• MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
• [code
• ProcMEM: Learning Reusable Procedural Memory from Experience via Non-Parametric PPO for LLM Agents
• [code
• MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
• [code
• Self-Evolving Multi-Agent Systems via Decentralized Memory
• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
• MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
• Neural Garbage Collection: Learning to Forget while Learning to Reason
• Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents
• End-to-End Test-Time Training for Long Context
• [code
• ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
• [code
• MemEvolve: Meta-Evolution of Agent Memory Systems