Related papers: ARC-TGI: Human-Validated Task Generators with Reas…

Thanks to unprecedented language understanding and generation capabilities of large language model (LLM), Retrieval-augmented Code Generation (RaCG) has recently been widely utilized among software developers. While this has increased…

The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic…

Transformer-decoder language models are a core innovation in text based generative artificial intelligence. These models are being deployed as general-purpose intelligence systems in many applications. Central to their utility is the…

Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation…

Agentic Retrieval-Augmented Generation (Agentic RAG) has become a widely adopted paradigm for multi-hop question answering and complex knowledge reasoning, where retrieval and reasoning are interleaved at inference time. As reasoning…

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching…

Hierarchical Reasoning Model (HRM) is a novel approach using two small neural networks recursing at different frequencies. This biologically inspired method beats Large Language models (LLMs) on hard puzzle tasks such as Sudoku, Maze, and…

Recent advances in agentic frameworks have enabled AI agents to perform complex reasoning and decision-making. However, evidence comparing their reasoning performance, efficiency, and practical suitability remains limited. To address this…

Agentic tasks, which require multi-step problem solving with autonomy, tool use, and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. However, existing instruction data lacks tool interaction, and…

The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose a neuro-symbolic approach that combines a transformer for…

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent…

Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether…

Code completion has become an essential component of integrated development environments. Contemporary code completion methods rely on the abstract syntax tree (AST) to generate syntactically correct code. However, they cannot fully capture…

We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing explainable reasoning without the need of any…

How to evaluate Artificial General Intelligence (AGI) is a critical problem that is discussed and unsolved for a long period. In the research of narrow AI, this seems not a severe problem, since researchers in that field focus on some…

Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces…

Despite great success has been achieved in activity analysis, it still has many challenges. Most existing work in activity recognition pay more attention to design efficient architecture or video sampling strategy. However, due to the…

Deriving inference from heterogeneous inputs (such as images, text, and audio) is an important skill for humans to perform day-to-day tasks. A similar ability is desirable for the development of advanced Artificial Intelligence (AI)…

This study investigates whether assessments fostering higher-order thinking skills can reduce plagiarism involving generative AI tools. Participants completed three tasks of varying complexity in four groups: control, e-textbook, Google,…

Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-specific problems. Traditional RAG systems primarily rely on…