Related papers: Think Like Human Developers: Harnessing Community …

While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM…

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains…

Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often overlooked the…

Large Language Models (LLMs) show strong reasoning ability in open-domain question answering, yet their reasoning processes are typically linear and often logically inconsistent. In contrast, real-world reasoning requires integrating…

Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We collect pairs of naturalistic and synthetic reasoning tasks to…

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a…

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…

Large Language Models (LLMs) (e.g., ChatGPT) have shown impressive performance in code generation. LLMs take prompts as inputs, and Chain-of-Thought (CoT) prompting is the state-of-the-art prompting technique. CoT prompting asks LLMs first…

The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluations are susceptible to stylistic biases, and…

The reasoning capabilities of Large Language Models (LLMs) are increasingly attributed to training data quality rather than mere parameter scaling. However, existing data-centric paradigms often equate quality with factuality or diversity…

Human language offers a powerful window into our thoughts -- we tell stories, give explanations, and express our beliefs and goals through words. Abundant evidence also suggests that language plays a developmental role in structuring our…

While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous…

Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and…

Large Language Models (LLMs) excel in diverse areas, yet struggle with complex scientific reasoning, especially in the field of chemistry. Different from the simple chemistry tasks (e.g., molecule classification) addressed in previous…

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking…

Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advances in reasoning capabilities have significantly enhanced…

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…

Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance…

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…