Related papers: Inducing Overthink: Hierarchical Genetic Algorithm…

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…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Recent advances in Large Language Models (LLMs) have driven interest in automating cybersecurity penetration testing workflows, offering the promise of faster and more consistent vulnerability assessment for enterprise systems. Existing LLM…

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference. However, applying elaborate reasoning for all queries often results in…

Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multimodal knowledge during generation. However, the underlying retrieval databases may naturally contain,…

Recently, techniques such as explicit structured reasoning have demonstrated strong test-time scaling behavior by enforcing a separation between the model's internal "thinking" process and the final response. A key factor influencing answer…

The recent rise of Large Reasoning Models (LRMs) has significantly improved multi-step reasoning performance, but often at the cost of generating excessively long reasoning chains. This paper revisits the efficiency of such reasoning…

Recent advancements in large reasoning models (LRMs) like DeepSeek-R1 and OpenAI o1 series have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT). However, a…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become a core technology for tasks such as question-answering (QA) and content generation. RAG poisoning is an attack method to induce LLMs to generate…

Efficient retrieval of external knowledge bases and web pages is crucial for enhancing the reasoning abilities of LLMs. Previous works on training LLMs to leverage external retrievers for solving complex problems have predominantly employed…

While inference-time thinking allows Large Language Models (LLMs) to address complex problems, the extended thinking process can be unreliable or inconsistent because of the model's probabilistic nature, especially near its knowledge…

The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference. These models employ extended chain-of-thought (CoT) processes, exploring multiple…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed…

O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs. By applying test-time scaling to generate extended reasoning paths, they establish many SOTAs across a wide range of…

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

The rapid expansion of IoT deployments has intensified cybersecurity threats, notably Distributed Denial of Service (DDoS) attacks, characterized by increasingly sophisticated patterns. Leveraging Generative AI through On-Device Large…

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…