相关论文: BOOKMARKS: Efficient Active Storyline Memory for R…

Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel". We dwell on our actions in the past and experience satisfaction or regret. More than merely autobiographical storytelling, we use these event…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Every individual carries a unique and personal life story shaped by their memories and experiences. However, these memories are often scattered and difficult to organize into a coherent narrative, a challenge that defines the task of…

Role-Playing Agents (RPAs), benefiting from large language models, is an emerging interactive AI system that simulates roles or characters with diverse personalities. However, existing methods primarily focus on mimicking dialogues among…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic…

Tracking characters and locations throughout a story can help improve the understanding of its plot structure. Prior research has analyzed characters and locations from text independently without grounding characters to their locations in…

We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we…

As an effective method to boost the performance of Large Language Models (LLMs) on the question answering (QA) task, Retrieval-Augmented Generation (RAG), which queries highly relevant information from external complex documents, has…

Role-playing conversational agents (RPCAs) face persistent challenges in maintaining role consistency. To address this, we propose RAIDEN-R1, a novel reinforcement learning framework that integrates Verifiable Role-Awareness Reward (VRAR).…

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…

Many manipulation tasks require memory beyond the current observation, yet most visuomotor policies rely on the Markov assumption and thus struggle with repeated states or long-horizon dependencies. Existing methods attempt to extend…

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

As LLMs exhibit a high degree of human-like capability, increasing attention has been paid to role-playing research areas in which responses generated by LLMs are expected to mimic human replies. This has promoted the exploration of…

We describe a method for proactive information retrieval targeted at retrieving relevant information during a writing task. In our method, the current task and the needs of the user are estimated, and the potential next steps are…

Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting in suboptimal…

We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…

Reward modeling has become a cornerstone of aligning large language models (LLMs) with human preferences. Yet, when extended to subjective and open-ended domains such as role play, existing reward models exhibit severe degradation,…

Storyline visualizations are an effective means to present the evolution of plots and reveal the scenic interactions among characters. However, the design of storyline visualizations is a difficult task as users need to balance between…

Humans exhibit complex motions that vary depending on the task that they are performing, the interactions they engage in, as well as subject-specific preferences. Therefore, forecasting future poses based on the history of the previous…