Related papers: Graph-Native Cognitive Memory for AI Agents: Forma…
The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems. Existing methodologies…
AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural…
Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory. Recent efforts address these limitations via external memory…
The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and…
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…
Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query…
To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates…
External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…
Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal,…
Persistent memory is a central capability for AI agents, yet the mathematical foundations of memory retrieval, lifecycle management, and consistency remain unexplored. Current systems employ cosine similarity for retrieval, heuristic decay…
This study aims to systematically evaluate the performance of large language models (LLMs) in abstract visual reasoning problems. We examined four LLM models (GPT-4.1-Mini, Claude-3.5-Haiku, Gemini-1.5-Flash, Llama-3.3-70b) utilizing four…
Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues.…
Distributed multi-agent systems (DMAS) based on large language models (LLMs) enable collaborative intelligence while preserving data privacy. However, systematic evaluations of long-term memory under network constraints are limited. This…
Modern large language model-based reasoning systems frequently recompute similar reasoning steps across tasks, wasting computational resources, inflating inference latency, and limiting reproducibility. These inefficiencies underscore the…
Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical…
AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a…
Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of…
We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype…
Approximate Nearest Neighbor Search (ANNS) is a core primitive in modern AI systems, and graph-based methods currently offer the best accuracy-efficiency trade-off at scale. The workload is fundamentally memory-bound: graph traversal…