Related papers: interwhen: A Generalizable Framework for Steering …

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…

Large Reasoning Models (LRMs) achieve strong performance through explicit chain-of-thought reasoning but suffer from \textit{overthinking}: generating excessive reasoning tokens even for trivial queries. {Beyond inflating cost, overthinking…

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but inherently sequential decoding leads to substantial latency, especially on complex tasks. Recent work on adaptive…

Hybrid reasoning systems that combine learned components with model-based inference are increasingly deployed in tool-augmented decision loops, yet their runtime behavior under partial observability and sustained evidence mismatch remains…

Despite impressive advances in large language models (LLMs), existing benchmarks often focus on single-turn or single-step tasks, failing to capture the kind of iterative reasoning required in real-world settings. To address this…

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is…

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanations. We address this by generating reasoning trajectories for six medical VQA benchmarks…

Vision-Language Models (VLMs) remain limited in spatial reasoning tasks that require multi-view understanding and embodied perspective shifts. Recent approaches such as MindJourney attempt to mitigate this gap through test-time scaling…

Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form…

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…

Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has…

Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. One solution is to route intermediate chain-of-thought (CoT)…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt a linear pipeline of plan to search to write to a report,…

As Large Language Models increasingly automate complex, long-horizon tasks such as \emph{vibe coding}, a supervision gap has emerged. While models excel at execution, users often struggle to guide them effectively due to insufficient domain…

Scaling test-time compute has emerged as a key strategy for enhancing the reasoning capabilities of large language models (LLMs), particularly in tasks like mathematical problem-solving. A traditional approach, Self-Consistency (SC),…

Large language models (LLMs) now exhibit strong multi-step reasoning abilities, but existing inference-time scaling methods remain computationally expensive, often relying on extensive sampling or external evaluators. We propose a…

Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence…