Related papers: SPECA: Specification-to-Checklist Agentic Auditing…

This paper proposes a new methodology for early validation of high-level requirements on cyber-physical systems with the aim of improving their quality and, thus, lowering chances of specification errors propagating into later stages of…

Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy,…

We present SPEAR, a multi-agent coordination framework for smart contract auditing that applies established MAS patterns in a realistic security analysis workflow. SPEAR models auditing as a coordinated mission carried out by specialized…

Effective features are crucial for predictive model performance, but creating them often requires domain expertise, limiting scalability across applications. We define feature engineering as an agentic code generation problem: features are…

Formal verification of smart contracts has become a hot topic in academic and industrial research, given the growing value of assets managed by decentralized applications and the consequent incentive for adversaries to tamper with them.…

LLM-based tools are automating more software development tasks at a rapid pace, but there is no rigorous way to evaluate how different architectural choices -- prompts, skills, tools, multi-agent setups -- materially affect both capability…

Turing completeness has made Ethereum smart contracts attractive to blockchain developers and attackers alike. To increase code security, many tools can now spot most known vulnerabilities$-$at the cost of production efficiency. Recent…

In recent years, the importance of smart contract security has been heightened by the increasing number of attacks against them. To address this issue, a multitude of static application security testing (SAST) tools have been proposed for…

EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…

Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end…

Correctness alone is insufficient: LLM-generated programs frequently satisfy unit tests while violating contest time or memory budgets. We present SwiftSolve, a complexity-aware multi-agent system for competitive programming that couples…

Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…

Building human-like agent, which aims to learn and think like human intelligence, has long been an important research topic in AI. To train and test human-like agents, we need an environment that imposes the agent to rich multimodal…

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving…

As autonomous code agents move toward end-to-end software development, evaluating their practical autonomy becomes critical. Current benchmarks hide friction by testing agents in pre-configured environments, and their static evaluation…

Text-to-SQL systems have become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as…

Formal verification of multi-agent systems is hard, both theoretically and in practice. In particular, studies that use a single verification technique typically show limited efficiency, and allow to verify only toy examples. Here, we…

The development of large, software-intensive systems is a complex undertaking that we generally tackle by a divide and conquer strategy. Companies thereby face the challenge of coordinating individual aspects of software development, in…

There is a huge demand to ensure the compliance of smart contracts listed on blockchain platforms to safety and economic standards. Today, manual efforts in the form of auditing are commonly used to achieve this goal. ML-based automated…

The rapid evolution of Large Language Models' has underscored the need for evaluation frameworks that are globally applicable, flexible, and modular, and that support a wide range of tasks, model types, and linguistic settings. We introduce…