Memorix: Managing Memory Selections for AI Agents
cs.OS, cs.AI
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/volcengine/OpenViking
Project page: https://ostreedev.github.io/ostree/repo
Terminology
Sources
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- Functional Package Management with Guix
- SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
- AgentOps: Enabling Observability of LLM Agents
- DeltaBox: Millisecond-Scale Sandbox Checkpoint and Rollback for Stateful AI Agents
- LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
- Measuring AI Ability to Complete Long Software Tasks
- Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
- MemOS: A Memory OS for AI System
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Kosmos: An AI Scientist for Autonomous Discovery
- MemGPT: Towards LLMs as Operating Systems
- PostTrainBench: Can LLM Agents Automate LLM Post-Training?
- Agentic Much? Adoption of Coding Agents on GitHub
- Codified Context: Infrastructure for AI Agents in a Complex Codebase
- On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
- RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- ReAct: Synergizing Reasoning and Acting in Language Models
- AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?