Related papers: EviMem: Evidence-Gap-Driven Iterative Retrieval fo…

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Sustaining long-term interactions remains a bottleneck for Large Language Models (LLMs), as their limited context windows struggle to manage dialogue histories that extend over time. Existing memory systems often treat interactions as…

Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and…

Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dialogue: (i) \textbf{disconnected evidence}, where multi-hop…

Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs' generation, necessitating the development of denoising…

Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when images are included, the user-specific information needed for later questions is typically…

Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a conversational memory…

Long-horizon applications increasingly require large language models (LLMs) to answer queries when relevant evidence is sparse and dispersed across very long contexts. Existing memory systems largely follow two paradigms: explicit…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory…

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and…

While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning benchmarks attempt to mitigate this using fictitious identities…

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by…

Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session…

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to…