English
Related papers

Related papers: Asking for Knowledge: Training RL Agents to Query …

200 papers

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as…

Artificial Intelligence · Computer Science 2024-07-01 Selene Baez Santamaria , Shihan Wang , Piek Vossen

Temporal Knowledge Graph Question Answering (TKGQA) is challenging because it requires multi-hop reasoning under complex temporal constraints. Recent LLM-based approaches have improved semantic modeling for this task, but many still rely on…

Computation and Language · Computer Science 2026-03-26 Xufei Lv , Jiahui Yang , Haoyuan Sun , Xialin Su , Zhiliang Tian , Yifu Gao , Linbo Qiao , Houde Liu

Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not sufficient, thus intrinsic reward formulations are needed to…

Machine Learning · Computer Science 2022-06-07 Patrik Reizinger , Márton Szemenyei

Can artificial agents learn to assist others in achieving their goals without knowing what those goals are? Generic reinforcement learning agents could be trained to behave altruistically towards others by rewarding them for altruistic…

Artificial Intelligence · Computer Science 2022-03-22 Tim Franzmeyer , Mateusz Malinowski , João F. Henriques

Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources,…

Computation and Language · Computer Science 2019-02-26 Igor Labutov , Bishan Yang , Anusha Prakash , Amos Azaria

This paper argues that Active Inference (AIF) provides a crucial foundation for developing autonomous AI agents capable of learning from experience without continuous human reward engineering. As AI systems begin to exhaust high-quality…

Artificial Intelligence · Computer Science 2025-08-08 Bo Wen

Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…

Artificial Intelligence · Computer Science 2024-04-05 Benedict Quartey , Ankit Shah , George Konidaris

Curiosity is an important factor that favors independent and individualized learning in children. Research suggests that it is also a competence that can be fostered by training specific metacognitive skills and information-searching…

Human-Computer Interaction · Computer Science 2023-01-12 Rania Abdelghani , Pierre-Yves Oudeyer , Edith Law , Catherine de Vulpillières , Hélène Sauzéon

Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without requiring an agent to interact with their environment, by…

Machine Learning · Computer Science 2019-03-01 Chris R. Serrano , Michael A. Warren

Question Answering (QA) is the task of automatically answering questions posed by humans in natural languages. There are different settings to answer a question, such as abstractive, extractive, boolean, and multiple-choice QA. As a popular…

Computation and Language · Computer Science 2023-04-07 Zhichao Duan , Xiuxing Li , Zhengyan Zhang , Zhenyu Li , Ning Liu , Jianyong Wang

Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems,…

Artificial Intelligence · Computer Science 2023-10-12 James R. Kirk , Robert E. Wray , John E. Laird

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to…

Computation and Language · Computer Science 2017-04-21 Bhuwan Dhingra , Lihong Li , Xiujun Li , Jianfeng Gao , Yun-Nung Chen , Faisal Ahmed , Li Deng

As reinforcement learning methods increasingly amass accomplishments, the need for comprehending their solutions becomes more crucial. Most explainable reinforcement learning (XRL) methods generate a static explanation depicting their…

Artificial Intelligence · Computer Science 2025-04-09 Yotam Amitai , Ofra Amir , Guy Avni

Reinforcement Learning (RL) agents often struggle in sparse-reward environments where traditional exploration strategies fail to discover effective action sequences. Large Language Models (LLMs) possess procedural knowledge and reasoning…

Machine Learning · Computer Science 2025-10-13 Vaibhav Jain , Gerrit Grossmann

Retrieval-augmented generation (RAG) is a common strategy to reduce hallucinations in Large Language Models (LLMs). While reinforcement learning (RL) can enable LLMs to act as search agents by activating retrieval capabilities, existing…

Computation and Language · Computer Science 2025-05-13 Ziyang Huang , Xiaowei Yuan , Yiming Ju , Jun Zhao , Kang Liu

Reinforcement learning (RL) trains agents to accomplish complex tasks through environmental interaction data, but its capacity is also limited by the scope of the available data. To obtain a knowledgeable agent, a promising approach is to…

Machine Learning · Computer Science 2024-04-16 Jing-Cheng Pang , Si-Hang Yang , Kaiyuan Li , Jiaji Zhang , Xiong-Hui Chen , Nan Tang , Yang Yu

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation…

As reinforcement learning methods increasingly amass accomplishments, the need for comprehending their solutions becomes more crucial. Most explainable reinforcement learning (XRL) methods generate a static explanation depicting their…

Artificial Intelligence · Computer Science 2023-01-25 Yotam Amitai , Guy Avni , Ofra Amir

Search agents are language models (LMs) that reason and search knowledge bases (or the web) to answer questions; recent methods supervise only the final answer accuracy using reinforcement learning with verifiable rewards (RLVR). Most RLVR…

Machine Learning · Computer Science 2026-01-27 James Burgess , Jan N. Hansen , Duo Peng , Yuhui Zhang , Alejandro Lozano , Min Woo Sun , Emma Lundberg , Serena Yeung-Levy

Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios. Retrieval-Augmented Generation (RAG) introduces external knowledge but suffers from hallucinations and latency due to noisy retrievals.…

Computation and Language · Computer Science 2025-09-19 Bolei He , Xinran He , Run Shao , Shanfu Shu , Xianwei Xue , Mingquan Cheng , Haifeng Li , Zhenhua Ling