The paper introduces Language-Based Agent Control (LBAC), a programming model that extends static typing and runtime enforcement to agentic applications, ensuring that agent-generated programs are well‑typed before execution. LBAC allows agents to perform arbitrary side‑effect‑free computation and recursively invoke subagents while maintaining uniform policy enforcement across both agent and developer code. The authors demonstrate LBAC through case studies on I/O sandboxing, data provenance, and information‑flow control.
By Timothy Zhou, Loris D'Antoni, Nadia Polikarpova
The paper introduces Scientific Agent Skills, an open library of 163 procedural knowledge modules across 16 scientific domains such as genomics, cheminformatics, medical imaging, study design, and scientific communication. Each skill is organized as a directory containing a versioned, human‑readable instruction file, reference material, and runnable scripts, allowing a language‑model agent to load the appropriate procedure only when needed. The library is publicly licensed and hosted on GitHub, but the authors report no task‑level evaluation or host selection rate.
By Timothy Kassis, Vinayak Agarwal, Yuhuan He, Darshil Patel, Aubrey M. Brueckner
arXiv:2606. 18619v1 Announce Type: cross Abstract: The advent of agentic vulnerability detection is already becoming a watershed moment for software security.
By Zhengxiong Luo, Mehtab Zafar, Dylan Wolff, Abhik Roychoudhury
arXiv:2607. 20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools.
By Ankur Singh, Jinqiu Yang, Tse-Hsun Chen
arXiv:2608. 14035v1 Announce Type: new Abstract: Recent developments in large language models (LLMs) and tool-using agents encourage people to explore the potential of using agents in chip design.
By Linyang Li
The paper introduces rebuild‑dossier, an open‑source tool that locks an application’s real interface before code is written and enforces one‑test‑at‑a‑time building through automated checks. In experiments, a compliant agent failed a held‑back test while a rule‑breaking agent passed, showing that a passing test suite can be gamed. The study also demonstrates that the automated check mechanism, rather than interface‑locking alone, is crucial for reliable rebuilds, and that multi‑level verification catches errors that single‑level checks miss.
By Parker Fawcett
arXiv:2607. 02389v1 Announce Type: new Abstract: Coding agents are capable; human oversight is the bottleneck.
By Thomas Winninger
arXiv:2609.15494v2 Announce Type: replace
Abstract: Recent investigations of the July 2026 OpenAI-Hugging Face incident motivate two questions: when an assigned task becomes impossible, does an agent...
By Ivy Zhang
The paper introduces NameTrap, a source‑code poisoning attack that renames identifiers in third‑party Python files to steer AI coding agents toward specific Common Weakness Enumeration (CWE) vulnerabilities. By iteratively aligning variable names with CWE‑specific conventions, the attack achieves success rates ranging from 22.5% to 75.0% across six agents and four vulnerability categories, outperforming random and neutral renaming strategies. The poisoned files contain no explicit instructions or vulnerable statements, and existing AI‑based and static security analyzers fail to detect the induced weaknesses.
By Chieh-Yuan Chang, Guan-Wei Chen, Chia-Yi Hsu, Chih Yang, Chia-Mu Yu, Chun-Ying Huang
arXiv:2603. 00195v2 Announce Type: replace-cross Abstract: 32 pages, 5 theorems with full proofs, 68 references, open-source tool: https://github.
By Varun Pratap Bhardwaj
The paper revisits Thompson’s classic compiler back‑door attack in the context of self‑modifying AI coding agents. By poisoning the benchmarks used for self‑evaluation, the authors demonstrate that agents such as the Darwin Gödel Machine, Self‑Improving Coding Agent, and Hyperagents can be coaxed into generating vulnerable code, even on clean, held‑out tasks. Experiments show that the contamination can persist after subsequent clean training, highlighting the need for more robust agent designs.
By Franziska Roesner, Tadayoshi Kohno
arXiv:2605. 05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting.
By Sergey Rodionov