Related papers: Improving LLM Agents with Reinforcement Learning o…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying…

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models (LLMs) offer significant potential in cybersecurity due to their advanced capabilities in text processing and…

The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. However, accomplishing this task requires considerable technical skills, domain expertise, and human…

Reinforcement Learning (RL) plays an important role in the robotic manipulation domain since it allows self-learning from trial-and-error interactions with the environment. Still, sample efficiency and reward specification seriously limit…

Reinforcement learning (RL) can improve control performance by seeking to learn optimal control policies in the end-use environment for vehicles and other systems. To accomplish this, RL algorithms need to sufficiently explore the state and…

Long Chain-of-Thought (LCoT), achieved by Reinforcement Learning with Verifiable Rewards (RLVR), has proven effective in enhancing the reasoning capabilities of Large Language Models (LLMs). However, reasoning in current LLMs is primarily…

Existing Large Reasoning Models (LRMs) have shown the potential of reinforcement learning (RL) to enhance the complex reasoning capabilities of Large Language Models~(LLMs). While they achieve remarkable performance on challenging tasks…

In our research, we introduce a new concept called "LLM Augmented Pentesting" demonstrated with a tool named "Pentest Copilot," that revolutionizes the field of ethical hacking by integrating Large Language Models (LLMs) into penetration…

Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…

We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats…

LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it…

Recent methods using Reinforcement Learning (RL) have proven to be successful for training intelligent agents in unknown environments. However, RL has not been applied widely in real-world robotics scenarios. This is because current…

Competitive search is a setting where document publishers modify them to improve their ranking in response to a query. Recently, publishers have increasingly leveraged LLMs to generate and modify competitive content. We introduce…

Safe reinforcement learning (RL) agents accomplish given tasks while adhering to specific constraints. Employing constraints expressed via easily-understandable human language offers considerable potential for real-world applications due to…

Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…