Related papers: The Cognitive Penalty: Ablating System 1 and Syste…

Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical…

Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action…

Large Language Models (LLMs) have the potential to enhance Agent-Based Modeling by better representing complex interdependent cybersecurity systems, improving cybersecurity threat modeling and risk management. However, evaluating LLMs in…

The evaluation of Large Language Models (LLMs) remains challenging due to inconsistency, bias, and the absence of transparent decision criteria in automated judging. We present Debate, Deliberate, Decide (D3), a cost-aware, adversarial…

Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a challenge, particularly for underrepresented regions. In this…

The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices. However, Small Language Models (SLMs) often face a "reasoning gap", particularly in non-English languages like…

As Large Language Models (LLMs) achieve significant breakthroughs in complex reasoning tasks, evaluating their proficiency in science, technology, engineering, and mathematics (STEM) has become a primary method for measuring machine…

Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

Human-computer interaction (HCI) is significantly impacted by delayed responses from a spoken dialogue system. Hence, end-to-end (e2e) spoken language understanding (SLU) solutions have recently been proposed to decrease latency. Such…

Existing approaches to bias evaluation in large language models (LLMs) trade ecological validity for statistical control, relying either on artificial prompts that poorly reflect real-world use or on naturalistic tasks that lack scale and…

Causal reasoning is one of the primary bottlenecks that Large Language Models (LLMs) must overcome to attain human-level intelligence. Recent studies indicate that LLMs display near-random performance on reasoning tasks. To address this, we…

We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training by…

Deploying local large language models and vision-language models on edge devices requires balancing accuracy with constrained computational and energy budgets. Although graphics processors dominate modern artificial-intelligence deployment,…

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or…

Existing benchmarks for AI reasoning provide limited insight into how closely these capabilities resemble human reasoning in naturalistic contexts. We present an adaptation of the Watson & Holmes detective tabletop game as a new benchmark…

Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong during token-by-token generation and how to narrow this gap…

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…