Related papers: SheetBrain: A Neuro-Symbolic Agent for Accurate Re…
Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reasoning structure helps, and when it instead reduces efficiency…
Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…
Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…
Scene graphs have emerged as a structured and serializable environment representation for grounded spatial reasoning with Large Language Models (LLMs). In this work, we propose SG^2, an iterative Schema-Guided Scene-Graph reasoning…
We introduce SATBench, a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems. Unlike prior work that focuses on inference…
This paper presents a toolkit for spreadsheet visualization based on logical areas, semantic classes and data modules. Logical areas, semantic classes and data modules are abstract representations of spreadsheet programs that are meant to…
Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly when encountering out-of-distribution data. Neurosymbolic…
Large Language Models (LLMs) are increasingly deployed as reasoning systems, where reasoning paradigms - such as Chain-of-Thought (CoT) and multi-agent systems (MAS) - play a critical role, yet their relative effectiveness and cost-accuracy…
Over decades, neuroscience has accumulated a wealth of research results in the text modality that can be used to explore cognitive processes. Meta-analysis is a typical method that successfully establishes a link from text queries to brain…
Large language models (LLMs) with advanced cognitive capabilities are emerging as agents for various reasoning and planning tasks. Traditional evaluations often focus on specific reasoning or planning questions within controlled…
Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…
We present a hierarchical neuro-symbolic control framework that tightly couples a classical symbolic planner with a transformer-based policy to address long-horizon decision-making under uncertainty. At the high level, the planner assembles…
With the development of artificial intelligence (AI), large language models (LLM) are widely used in many fields. However, the reasoning ability of LLM is still very limited when it comes to mathematical reasoning. Mathematics plays an…
Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. This has led to the development of…
To enable robots to comprehend high-level human instructions and perform complex tasks, a key challenge lies in achieving comprehensive scene understanding: interpreting and interacting with the 3D environment in a meaningful way. This…
Equation discovery from data is a central challenge in machine learning for science, which requires the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent large language model (LLM)…
Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning. This paper introduces a novel neurosymbolic…
Spreadsheets are the go-to tool for computerized calculation and modelling, but are hard to comprehend and adapt after reaching a certain complexity. In general, cognition of complex systems is facilitated by having a higher order mental…
The ability of large language models (LLMs) to mimic human-like intelligence has led to a surge in LLM-based autonomous agents. Though recent LLMs seem capable of planning and reasoning given user instructions, their effectiveness in…
The cognitive and reasoning abilities of large language models (LLMs) have enabled remarkable progress in natural language processing. However, their performance in interpreting structured data, especially in tabular formats, remains…