相关论文: Ever-Evolving Memory by Blending and Refining the …

Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context. In contrast, the long-term conversation setting has hardly been studied. In this work…

Enabling bi-directional retrieval of images and texts is important for understanding the correspondence between vision and language. Existing methods leverage the attention mechanism to explore such correspondence in a fine-grained manner.…

This research investigates the application of Large Language Models (LLMs) to augment conversational agents in process mining, aiming to tackle its inherent complexity and diverse skill requirements. While LLM advancements present novel…

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,…

Large Language Models (LLMs) have emerged as a new paradigm for recommendation by converting interacted item history into language modeling. However, constrained by the limited context length of LLMs, existing approaches have to truncate…

Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient…

Large language models (LLMs) operate within fixed context windows that fundamentally limit conversational continuity. When context fills, compaction discards history irreversibly; when sessions end, all memory resets to zero. Existing…

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However,…

Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of…

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

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 largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM…

Nowadays, the current neural network models of dialogue generation(chatbots) show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their…

Long-term memory systems enable conversational agents based on large language models (LLMs) to retain, retrieve, and apply user-specific information across multi-session interactions. However, existing evaluations mainly assess…

In the large language model (LLM) revolution, embedding is a key component of various systems, such as retrieving knowledge or memories for LLMs or building content moderation filters. As such cases span from English to other natural or…

The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously. This paper proposes…

Dialogue-based language models mark a huge milestone in the field of artificial intelligence, by their impressive ability to interact with users, as well as a series of challenging tasks prompted by customized instructions. However, the…

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…

Large Language Models (LLMs) have spurred interest in automatic evaluation methods for summarization, offering a faster, more cost-effective alternative to human evaluation. However, existing methods often fall short when applied to complex…