Related papers: unix-ctf: Procedural Environments for Unix-Compete…
We introduce CPP-UT-Bench, a benchmark dataset to measure C++ unit test generation capability of a large language model (LLM). CPP-UT-Bench aims to reflect a broad and diverse set of C++ codebases found in the real world. The dataset…
Efficient code retrieval is critical for developer productivity, yet existing benchmarks largely focus on Python and rarely stress-test robustness beyond superficial lexical cues. To address the gap, we introduce an automated pipeline for…
The constant-time programming discipline (CT) is an efficient countermeasure against timing side-channel attacks, requiring the control flow and the memory accesses to be independent from the secrets. Yet, writing CT code is challenging as…
Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…
Large Language Models (LLMs) are advancing at a rapid pace, with significant improvements at natural language processing and coding tasks. Yet, their ability to work with formal languages representing data, specifically within the realm of…
Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…
Collaborative problem solving (CPS) competence is considered one of the essential 21st-century skills. To facilitate the assessment and learning of CPS competence, researchers have proposed a series of frameworks to conceptualize CPS and…
Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \textit{catastrophic forgetting} (CF), which…
Competitive programming has become a popular way for programmers to test their skills. Large-scale online programming contests attract millions of experienced programmers to compete against each other. Competition-level programming problems…
The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…
Computer-Using Agents (CUAs) aim to autonomously operate computer systems to complete real-world tasks. However, existing agentic systems remain difficult to scale and lag behind human performance. A key limitation is the absence of…
LLMs used for code generation are typically guided by engineering constraints--technology choices, dependency restrictions, and architectural patterns--expressed in verbose natural language. We investigate whether compact, structured…
LLM-based vulnerability detectors are increasingly deployed in CI/CD security gating, yet their resilience to evasion under syntax- and compilation-preserving edits remains poorly understood. We evaluate five attack variants spanning four…
The overwhelming majority of survivable (fault-tolerant) network design models assume a uniform scenario set. Such a scenario set assumes that every subset of the network resources (edges or vertices) of a given cardinality $k$ comprises a…
Secret Unknown Ciphers (SUC) have been proposed recently as digital clone-resistant functions overcoming some of Physical(ly) Unclonable Functions (PUF) downsides, mainly their inconsistency because of PUFs analog nature. In this paper, we…
Evaluating Large Language Models (LLMs) on repository-level feature implementation is a critical frontier in software engineering. However, establishing a benchmark that faithfully mirrors realistic development scenarios remains a…
Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel…
Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false…
Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…
By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Because SFT and alignment…