相关论文: Do Coding Agents Understand Least-Privilege Author…

The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This position paper argues that personal-agent architecture must move to the edge because the…

Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…

Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which human developers naturally incorporate refactoring as part of…

Real-world applications routinely make authorization decisions based on dynamic computation. Reasoning about dynamically computed authority is challenging. Integrity of the system might be compromised if attackers can improperly influence…

Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and…

Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass ("jailbreak") attacks beyond text-only settings.…

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an…

Many of the challenges facing today's reinforcement learning (RL) algorithms, such as robustness, generalization, transfer, and computational efficiency are closely related to compression. Prior work has convincingly argued why minimizing…

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

We consider the problem of error control in a coded, multicast network, focusing on the scenario where the errors can occur only on a proper subset of the network edges. We model this problem via an adversarial noise, presenting a formal…

Modern software systems rely on mining insights from business sensitive data stored in public clouds. A data breach usually incurs significant (monetary) loss for a commercial organization. Conceptually, cloud security heavily relies on…

We address the self-stabilizing bit-dissemination problem, designed to capture the challenges of spreading information and reaching consensus among entities with minimal cognitive and communication capacities. Specifically, a group of $n$…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

Assessing the capabilities and risks of frontier AI systems is a critical area of research, and recent work has shown that repeated sampling from models can dramatically increase both. For instance, repeated sampling has been shown to…

Source code authorship attribution is an important problem often encountered in applications such as software forensics, bug fixing, and software quality analysis. Recent studies show that current source code authorship attribution methods…

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Decomposing hard problems into subproblems often makes them easier and more efficient to solve. With large language models (LLMs) crossing critical reliability thresholds for a growing slate of capabilities, there is an increasing effort to…

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Large language models (LLMs) are increasingly deployed in enterprise settings where they handle sensitive documents and user context, raising acute concerns over security and controllability. Conventional access control regulates whether…