We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate historical entities, predicates, and logical forms when inferring the logical form of current utterances. Dialog memory management is embodied in a generative model, in which a logical form is interpreted in a top-down manner following a small and flexible grammar. We learn the model from denotations without explicit annotation of logical forms, and evaluate it on a large-scale dataset consisting of 200K dialogs over 12.8M entities. Results verify the benefits of modeling dialog memory, and show that our semantic parsing-based approach outperforms a memory network based encoder-decoder model by a huge margin.

We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base. To handle enormous ellipsis phenomena in conversation, we introduce dialog memory management to manipulate historical entities, predicates, and logical forms when inferring the logical form of current utterances. Dialog memory management is embodied in a generative model, in which a logical form is interpreted in a top-down manner following a small and flexible grammar. We learn the model from denotations without explicit annotation of logical forms, and evaluate it on a large-scale dataset consisting of 200K dialogs over 12.8M entities. Results verify the benefits of modeling dialog memory, and show that our semantic parsing-based approach outperforms a memory network based encoder-decoder model by a huge margin.

Conversational AI systems often struggle with maintaining coherent, contextual memory across extended interactions, limiting their ability to provide personalized and contextually relevant responses. This paper presents IMDMR (Intelligent Multi-Dimensional Memory Retrieval), a novel system that addresses these limitations through a multi-dimensional search architecture. Unlike existing memory systems that rely on single-dimensional approaches, IMDMR leverages six distinct memory dimensions-semantic, entity, category, intent, context, and temporal-to provide comprehensive memory retrieval capabilities. Our system incorporates intelligent query processing with dynamic strategy selection, cross-memory entity resolution, and advanced memory integration techniques. Through comprehensive evaluation against five baseline systems including LangChain RAG, LlamaIndex, MemGPT, and spaCy + RAG, IMDMR achieves a 3.8x improvement in overall performance (0.792 vs 0.207 for the best baseline). We present both simulated (0.314) and production (0.792) implementations, demonstrating the importance of real technology integration while maintaining superiority over all baseline systems. Ablation studies demonstrate the effectiveness of multi-dimensional search, with the full system outperforming individual dimension approaches by 23.3%. Query-type analysis reveals superior performance across all categories, particularly for preferences/interests (0.630) and goals/aspirations (0.630) queries. Comprehensive visualizations and statistical analysis confirm the significance of these improvements with p < 0.001 across all metrics. The results establish IMDMR as a significant advancement in conversational AI memory systems, providing a robust foundation for enhanced user interactions and personalized experiences.

Advances in large language models are making personalized AI agents a new research focus. While current agent systems primarily rely on personalized external memory databases to deliver customized experiences, they face challenges such as memory redundancy, memory staleness, and poor memory-context integration, largely due to the lack of effective memory updates during interaction. To tackle these issues, we propose a new memory management system designed for affective scenarios. Our approach employs a Bayesian-inspired memory update algorithm with the concept of memory entropy, enabling the agent to autonomously maintain a dynamically updated memory vector database by minimizing global entropy to provide more personalized services. To better evaluate the system's effectiveness in this context, we propose DABench, a benchmark focusing on emotional expression and emotional change toward objects. Experimental results demonstrate that, our system achieves superior performance in personalization, logical coherence, and accuracy. Ablation studies further validate the effectiveness of the Bayesian-inspired update mechanism in alleviating memory bloat. Our work offers new insights into the design of long-term memory systems.

The preserved data are exemplars used for replaying. However, existing methods use a static and ad hoc strategy for memory allocation, which is often sub-optimal.

Loneliness and social isolation pose significant emotional and health challenges, prompting the development of technology-based solutions for companionship and emotional support. This paper introduces Livia, an emotion-aware augmented reality (AR) companion app designed to provide personalized emotional support by combining modular artificial intelligence (AI) agents, multimodal affective computing, progressive memory compression, and AR driven embodied interaction. Livia employs a modular AI architecture with specialized agents responsible for emotion analysis, dialogue generation, memory management, and behavioral orchestration, ensuring robust and adaptive interactions. Two novel algorithms-Temporal Binary Compression (TBC) and Dynamic Importance Memory Filter (DIMF)-effectively manage and prioritize long-term memory, significantly reducing storage requirements while retaining critical context. Our multimodal emotion detection approach achieves high accuracy, enhancing proactive and empathetic engagement. User evaluations demonstrated increased emotional bonds, improved satisfaction, and statistically significant reductions in loneliness. Users particularly valued Livia's adaptive personality evolution and realistic AR embodiment. Future research directions include expanding gesture and tactile interactions, supporting multi-user experiences, and exploring customized hardware implementations.

Large Language Models (LLMs) face fundamental limitations in context management despite recent advances extending context windows to millions of tokens. We propose Cognitive Workspace, a novel paradigm that transcends traditional Retrieval-Augmented Generation (RAG) by emulating human cognitive mechanisms of external memory use. Drawing from cognitive science foundations including Baddeley's working memory model, Clark's extended mind thesis, and Hutchins' distributed cognition framework, we demonstrate that current passive retrieval systems fail to capture the dynamic, task-driven nature of human memory management. Our analysis of 2024-2025 developments reveals that while techniques like Infini-attention and StreamingLLM achieve impressive context lengths, they lack the metacognitive awareness and active planning capabilities essential for true cognitive extension. Cognitive Workspace addresses these limitations through three core innovations: (1) active memory management with deliberate information curation, (2) hierarchical cognitive buffers enabling persistent working states, and (3) task-driven context optimization that dynamically adapts to cognitive demands. Empirical validation demonstrates Cognitive Workspace achieves an average 58.6% memory reuse rate (ranging from 54-60% across different tasks) compared to 0% for traditional RAG, with 17-18% net efficiency gain despite 3.3x higher operation counts. Statistical analysis confirms these advantages with p < 0.001 and Cohen's d > 23 across multiple task types, establishing the first quantitative evidence for active memory superiority in LLM systems. We present a comprehensive theoretical framework synthesizing insights from 50+ recent papers, positioning Cognitive Workspace as a fundamental shift from information retrieval to genuine cognitive augmentation.

The proliferation of multi-agent systems (MAS) in complex, dynamic environments necessitates robust and efficient mechanisms for managing shared knowledge. A critical challenge is ensuring that distributed memories remain synchronized, relevant, and free from the accumulation of outdated or inconsequential data - a process analogous to biological forgetting. This paper introduces the Co-Forgetting Protocol, a novel, comprehensive framework designed to address this challenge by enabling synchronized memory pruning in MAS. The protocol integrates three key components: (1) context-aware semantic voting, where agents utilize a lightweight DistilBERT model to assess the relevance of memory items based on their content and the current operational context; (2) multi-scale temporal decay functions, which assign diminishing importance to memories based on their age and access frequency across different time horizons; and (3) a Practical Byzantine Fault Tolerance (PBFT)-based consensus mechanism, ensuring that decisions to retain or discard memory items are agreed upon by a qualified and fault-tolerant majority of agents, even in the presence of up to f Byzantine (malicious or faulty) agents in a system of N greater than or equal to 3f+1 agents. The protocol leverages gRPC for efficient inter-agent communication and Pinecone for scalable vector embedding storage and similarity search, with SQLite managing metadata. Experimental evaluations in a simulated MAS environment with four agents demonstrate the protocol's efficacy, achieving a 52% reduction in memory footprint over 500 epochs, 88% voting accuracy in forgetting decisions against human-annotated benchmarks, a 92% PBFT consensus success rate under simulated Byzantine conditions, and an 82% cache hit rate for memory access.

Large Language Models (LLMs) encounter severe memory inefficiencies during long-context inference due to conventional handling of key-value (KV) caches. In this work, we introduce a novel integration of PagedAttention with PyTorch's FlexAttention, addressing internal fragmentation and inefficiencies associated with monolithic KV cache allocations. Implemented within IBM's Foundation Model Stack (FMS), our fused attention kernel efficiently gathers scattered KV data. Our benchmarks on an NVIDIA L4 GPU (24GB) demonstrate significantly reduced inference latency, growing only linearly (~2x) with sequence length from 128 to 2048 tokens when utilizing a global KV cache, compared to exponential latency increases without caching. While peak memory usage remains largely unchanged for single-step evaluations (dominated by model weights and activations), paged attention causes minimal incremental memory usage, observable only at sequence lengths exceeding 2048 tokens due to its power-of-two cache allocations. We open-source the full implementation and discuss its implications for future long-context model deployment.