相关论文: Cross-Platform Evaluation of Reasoning Capabilitie…
The design of distributed autonomous systems for operation beyond reliable ground contact presents a fundamental tension: as round-trip communication latency grows, the set of decisions delegable to ground operators shrinks. This paper…
Recent advancements in foundation models have improved autonomous tool usage and reasoning, but their capabilities in map-based reasoning remain underexplored. To address this, we introduce MapEval, a benchmark designed to assess foundation…
Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the…
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…
This work investigates the reasoning and planning capabilities of foundation models and their scalability in complex, dynamic environments. We introduce PuzzlePlex, a benchmark designed to assess these capabilities through a diverse set of…
MareNostrum5 is a pre-exascale supercomputer at the Barcelona Supercomputing Center (BSC), part of the EuroHPC Joint Undertaking. With a peak performance of 314 petaflops, MareNostrum5 features a hybrid architecture comprising Intel…
This paper presents preliminary results in the definition of a comprehensive benchmark framework designed to systematically evaluate spatial reasoning capabilities in neural networks, with a particular focus on morphological properties such…
Recent advances in Multi-Modal Large Language Models (MLLMs) have enabled unified processing of language, vision, and structured inputs, opening the door to complex tasks such as logical deduction, spatial reasoning, and scientific…
The use of Large Language Models (LLMs) in mathematical reasoning has become a cornerstone of related research, demonstrating the intelligence of these models and enabling potential practical applications through their advanced performance,…
High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on six diagnostic tasks spanning three settings: reasoning under…
We introduce TableVista, a comprehensive benchmark for evaluating foundation models in multimodal table reasoning under visual and structural complexity. TableVista consists of 3,000 high-quality table reasoning problems, where each…
Recent large language models (LLMs) achieve near-saturation accuracy on many established mathematical reasoning benchmarks, raising concerns about their ability to diagnose genuine reasoning competence. This saturation largely stems from…
The capability of Unified Multimodal Models (UMMs) to apply world knowledge across diverse tasks remains a critical, unresolved challenge. Existing benchmarks fall short, offering only siloed, single-task evaluations with limited diagnostic…
Algebraic reasoning remains one of the most informative stress tests for large language models, yet current benchmarks provide no mechanism for attributing failure to a specific cause. When a model fails an algebraic problem, a single…
Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…
A variety of logical frameworks support the use of higher-order abstract syntax (HOAS) in representing formal systems. Although these systems seem superficially the same, they differ in a variety of ways; for example, how they handle a…
Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason correctly. Current…
The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…
Structure reasoning is a fundamental capability of large language models (LLMs), enabling them to reason about structured commonsense and answer multi-hop questions. However, existing benchmarks for structure reasoning mainly focus on…
Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and…