Related papers: Pen-Strategist: A Reasoning Framework for Penetrat…

As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…

Large language model agents for data analysis typically generate and execute code directly on databases. However, when applied to sensitive data, this approach poses significant security risks. To address this issue, we propose a…

Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate the key factors that drive agent success and provide a…

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across…

Large Language Models have achieved strong performance on reasoning tasks, solving competition-level coding and math problems. However, their scalability is limited by human-labeled datasets and the lack of large-scale, challenging coding…

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Large Language Models (LLMs) are increasingly deployed in critical applications requiring reliable reasoning, yet their internal reasoning processes remain difficult to evaluate systematically. Existing methods focus on final-answer…

Programmatic reinforcement learning (PRL) has been explored for representing policies through programs as a means to achieve interpretability and generalization. Despite promising outcomes, current state-of-the-art PRL methods are hindered…

Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities in solving complex problems. However, current approaches primarily enhance reasoning through the elaboration of thoughts while neglecting the diversity of…

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing…

Strategic decision-making involves interactive reasoning where agents adapt their choices in response to others, yet existing evaluations of large language models (LLMs) often emphasize Nash Equilibrium (NE) approximation, overlooking the…

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that…

Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs…

Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time…

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generation (RAG) allows LLMs…

Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, yet their ability to perform structured symbolic planning remains limited, particularly in domains requiring formal representations like the…

Large Language Models (LLMs) are widely applied to downstream domains. However, current LLMs for high-stakes domain tasks, such as financial investment and legal QA, typically generate brief answers without reasoning processes and…

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover can achieve…