MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-10
Code: https://github.com/theseus-labs-rsi/MemTrace
Sources
- Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading
- Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- Self-GC: Self-Governing Context for Long-Horizon LLM Agents
- DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
- MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
- A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- Context as a Tool: Context Management for Long-Horizon SWE-Agents
- MemGPT: Towards LLMs as Operating Systems
- Generative Agents: Interactive Simulacra of Human Behavior
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Cognitive Architectures for Language Agents
- Scaling Long-Horizon LLM Agent via Context-Folding
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