Tag
LifeMem is a lifelong learning framework that enables LLM agents to transfer knowledge across multiple environments by clustering interaction trajectories to extract reusable skills, reducing forgetting and improving cross-task transfer.
EM^2Mem proposes an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors for compact, generation-ready memory in long-video question answering, improving accuracy and reducing latency.
ArborMem introduces an online memory framework for large language models that represents conversations as a navigable forest of interaction states, outperforming baselines on memory benchmarks and introducing BranchMemEval as a new diagnostic benchmark.
This paper introduces a Self-Evolving Just-In-Time Memory framework for proactive embodied safety, combining a Risk-Sufficient Topological Belief Graph, Agency-Grounded Factual Memory, and Experience Memory to mitigate hazards without stalling task progress. Experiments on IS-Bench show significant Safe-Success rate improvements (e.g., +30.3% on Qwen3-VL-8B).
SelfMem introduces a self-optimizing memory framework for AI agents that allows them to explore, evaluate, and refine their own memory strategies through memory tools and feedback signals, achieving significant improvements over baselines on the BEAM benchmark across large conversation scales.
Introduces DMF, a deterministic memory framework for conversational AI agents that replaces LLM-based compression with classical NLP and mathematical scoring, achieving comparable accuracy to Mem0 while using zero tokens for memory preparation and up to 242× fewer tokens overall.
Introduces a framework for agent memory with three components: Remember (hot session and cross-session storage), Cite (authority ordering via AGENTS.md), and Forget (timestamped facts with Mem0-style soft decay). Argues that missing any of these leads to stale facts or unauthorized sources.
This article introduces the open-source EverOS project, which provides long-term memory capabilities for AI coding assistants like Claude Code. It automatically saves conversation history and retrieves memories in new conversations. Additionally, it includes multiple application examples.
MemForest proposes a memory framework for long-context LLM agents that improves scalability and reduces latency through parallel chunk extraction and hierarchical temporal indexing, achieving 6x higher throughput on benchmarks.
Echo-Forcing introduces a scene memory framework for interactive long video generation, using hierarchical temporal memory, scene recall frames, and difference-aware memory decay to handle prompt switching and long-term recall. The method is training-free and achieves strong performance on VBench-Long.
Introduces SimpleMem, an efficient memory framework for LLM agents that uses semantic lossless compression to improve accuracy and reduce token consumption, achieving 26.4% F1 improvement and up to 30x reduction in inference-time token usage.