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

Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in…

Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented generation (RAG) mitigates this issue but lacks reliable…

Separating disinformation from fact on the web has long challenged both the search and the reasoning powers of humans. We show that the reasoning power of large language models (LLMs) and the retrieval power of modern search engines can be…

Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response generation, making performance significantly dependent on…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

Long-term conversational agents need memory systems that capture relationships between events, not merely isolated facts, to support temporal reasoning and multi-hop question answering. Current approaches face a fundamental trade-off: flat…

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features…

Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory…

Long-horizon interactive agents often accumulate large trajectory histories yet still fail to answer questions about earlier events reliably. We argue that the main bottleneck is not context length alone, but the trajectory-to-answer…

The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy. While latent memory offers a solution,…

Interactive medical consultation requires an agent to proactively elicit missing clinical evidence under uncertainty. Yet existing evaluations largely remain static or outcome-centric, neglecting the evidence-gathering process. In this…

Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as…

Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments. To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism…

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Memory performance is often the main bottleneck in modern computing systems. In recent years, researchers have attempted to scale the memory wall by leveraging new technology such as CXL, HBM, and in- and near-memory processing. Developers…

Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for temporally…

Emotion Recognition in Conversation~(ERC) across modalities is of vital importance for a variety of applications, including intelligent healthcare, artificial intelligence for conversation, and opinion mining over chat history. The crux of…

Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models'…

Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries,…

Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often…