English
Related papers

Related papers: Can Complexity and Uncomputability Explain Intelli…

200 papers

Over the last thirty years, considerable progress has been made with the development of systems that can drive cars, play games, predict protein folding and generate natural language. These systems are described as intelligent and there has…

Artificial Intelligence · Computer Science 2025-06-02 David Gamez

Recent breakthroughs in Large Reasoning Models (LRMs) have demonstrated that extensive Chain-of-Thought (CoT) generation is critical for enabling intricate cognitive behaviors, such as self-verification and backtracking, to solve complex…

Artificial Intelligence · Computer Science 2026-01-09 Minda Hu , Zexuan Qiu , Zenan Xu , Kun Li , Bo Zhou , Irwin King

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities by scaling up the length of Chain-of-Thought (CoT). However, excessively long reasoning traces pose substantial challenges for training cost and inference latency.…

Machine Learning · Computer Science 2026-01-09 Wenhao Zeng , Yaoning Wang , Chao Hu , Yuling Shi , Chengcheng Wan , Hongyu Zhang , Xiaodong Gu

The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…

Large language models (LLMs) remain broadly open and highly steerable: they imitate at scale, accept arbitrary system prompts, and readily adopt multiple personae. By analogy to human development, we hypothesize that progress toward…

Artificial Intelligence · Computer Science 2025-10-24 Marcelo Maciel Amaral , Raymond Aschheim

The demand for open and trustworthy AI models points towards widespread publishing of model weights. Consumers of these model weights must be able to act accordingly with the information provided. That said, one of the simplest AI…

Machine Learning · Computer Science 2024-06-21 Danial Dervovic , Freddy Lécué , Nicolás Marchesotti , Daniele Magazzeni

Functionality or proxy-based approach is one of the used approaches to evaluate the quality of explainable artificial intelligence methods. It uses statistical methods, definitions and new developed metrics for the evaluation without human…

Machine Learning · Computer Science 2025-02-04 Ahmed M. Salih

This paper compares model-agnostic and model-specific approaches to explainable AI (XAI) in deep learning image classification. I examine how LIME and SHAP (model-agnostic methods) differ from Grad-CAM and Guided Backpropagation…

Artificial Intelligence · Computer Science 2025-04-08 Keerthi Devireddy

The alignment between human objectives and machine learning models built on these objectives is a crucial yet challenging problem for achieving Trustworthy AI, particularly when preparing for superintelligence (SI). First, given that SI…

Artificial Intelligence · Computer Science 2024-12-11 Yosuke Miyanishi , Keita Mitani

This paper introduces an interdisciplinary framework called Machine Psychology, which merges principles from operant learning psychology with a specific Artificial Intelligence model, the Non-Axiomatic Reasoning System (NARS), to enhance…

Artificial Intelligence · Computer Science 2024-05-31 Robert Johansson

The construction of artificial general intelligence (AGI) was a long-term goal of AI research aiming to deal with the complex data in the real world and make reasonable judgments in various cases like a human. However, the current AI…

Artificial Intelligence · Computer Science 2019-09-23 Xin Su , Shangqi Guo , Feng Chen

Krakauer, Krakauer, and Mitchell (2025) distinguish between emergent capabilities and emergent intelligence, arguing that true intelligence requires efficient coarse-grained representations enabling diverse problem-solving through analogy…

Computation and Language · Computer Science 2026-03-10 Daniel Kilov

We propose a hybrid Artificial Intelligence (AI) climate modeling approach that enables climate modelers in scientific discovery using a climate-targeted simulation methodology based on a novel combination of deep neural networks and…

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where…

Foundation models excel in stable environments, yet often fail where reliability matters most: medicine, finance, and policy. This Fidelity Paradox is not just a data problem; it is structural. In domains where rules change over time, extra…

Machine Learning · Computer Science 2026-03-27 Steffen Lukas

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it…

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…

Artificial Intelligence · Computer Science 2025-01-29 Zeki Doruk Erden , Boi Faltings

Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Beichen Zhang , Yuhang Zang , Xiaoyi Dong , Yuhang Cao , Haodong Duan , Dahua Lin , Jiaqi Wang

Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently critical for…

Artificial Intelligence · Computer Science 2025-12-22 Yushi Feng , Junye Du , Yingying Hong , Qifan Wang , Lequan Yu

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a…

Computation and Language · Computer Science 2021-05-12 Diego Antognini , Boi Faltings