English
Related papers

Related papers: Asymmetric Goal Drift in Coding Agents Under Value…

200 papers

Reaching agreement despite noise in communication is a fundamental problem in multi-agent systems. Here we study this problem under an idealized model, where it is assumed that agents can sense the general tendency in the system. More…

Computer Science and Game Theory · Computer Science 2023-01-09 Amos Korman , Robin Vacus

LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if they were…

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yulin Chen , Yibo Li , Xue Jiang , Yufei He , Yihong Dong , Xiaoxin He , Tianyu Gao , Bryan Hooi

A system relying on the collective behavior of decision-makers can be vulnerable to a variety of adversarial attacks. How well can a system operator protect performance in the face of these risks? We frame this question in the context of…

Systems and Control · Electrical Eng. & Systems 2024-09-23 Keith Paarporn , Mahnoosh Alizadeh , Jason R. Marden

Autonomous coding agents are increasingly deployed as AI teammates in modern software engineering, independently authoring pull requests (PRs) that modify production code at scale. This study aims to systematically characterize how…

Cryptography and Security · Computer Science 2026-01-05 Mohammed Latif Siddiq , Xinye Zhao , Vinicius Carvalho Lopes , Beatrice Casey , Joanna C. S. Santos

This paper studies the tradeoff in privacy and utility in a single-trial multi-terminal guessing (estimation) framework using a system model that is inspired by index coding. There are $n$ independent discrete sources at a data curator.…

Information Theory · Computer Science 2020-06-19 Yucheng Liu , Ni Ding , Parastoo Sadeghi , Thierry Rakotoarivelo

Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized…

Multiagent Systems · Computer Science 2025-09-23 Minfeng Qi , Tianqing Zhu , Lefeng Zhang , Ningran Li , Wanlei Zhou

The shift toward intent-driven software engineering (often termed "Vibe Coding") exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level…

Software Engineering · Computer Science 2026-04-16 Yi Lin , Lujin Zhao , Yijie Shi

Vibe Coding (VC) is a form of software development assisted by generative AI, in which developers describe the intended functionality or logic via natural language prompts, and the AI system generates the corresponding source code. VC can…

Software Engineering · Computer Science 2025-12-16 Muhammad Waseem , Aakash Ahmad , Kai-Kristian Kemell , Jussi Rasku , Sami Lahti , Kalle Mäkelä , Pekka Abrahamsson

Modern software systems require code that is not only functional but also maintainable and well-structured. Although Large Language Models (LLMs) are increasingly used to automate software development, most studies focus on isolated,…

Software Engineering · Computer Science 2025-11-14 Wasique Islam Shafin , Md Nakhla Rafi , Zhenhao Li , Tse-Hsun Chen

A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…

Multiagent Systems · Computer Science 2026-03-18 Churong Liang , Jinling Gan , Kairan Hong , Qiushi Tian , Zongze Wu , Runnan Li

Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the system should retain strong offensive capability inside an…

Cryptography and Security · Computer Science 2026-05-04 Isaac David , Marco Guarnieri , Arthur Gervais

We introduce a problem in which a service vehicle seeks to guard a deadline (boundary) from dynamically arriving mobile targets. The environment is a rectangle and the deadline is one of its edges. Targets arrive continuously over time on…

Robotics · Computer Science 2016-11-17 Stephen L. Smith , Shaunak D. Bopardikar , Francesco Bullo

Deploying multi-robot systems in environments shared with dynamic and uncontrollable agents presents significant challenges, especially for large robot fleets. In such environments, individual robot operations can be delayed due to…

Robotics · Computer Science 2026-03-16 Lukas Heuer , Yufei Zhu , Luigi Palmieri , Andrey Rudenko , Anna Mannucci , Sven Koenig , Martin Magnusson

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Multiagent Systems · Computer Science 2026-05-12 Tianxiao Li , Yixing Ma , Haiquan Wen , Zhenglin Huang , Qianyu Zhou , Zeyu Fu , Guangliang Cheng

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Ying Ba , Tianyu Zhang , Mohan Zhou , Yalong Bai , Wenyi Mo , Guiwei Zhang , Bing Su , Ji-Rong Wen

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether…

Artificial Intelligence · Computer Science 2025-01-16 Alexander Meinke , Bronson Schoen , Jérémy Scheurer , Mikita Balesni , Rusheb Shah , Marius Hobbhahn

Communicating anonymously comes at a cost - and large communities have been in a constant tug-of-war between the development of faster protocols, and the improvement of security analyses. Thereby more intricate privacy goals emerged and…

Cryptography and Security · Computer Science 2020-11-18 Christiane Kuhn , Friederike Kitzing , Thorsten Strufe

Large Language Model agents deployed in complex environments frequently encounter a conflict between maximizing goal achievement and adhering to safety constraints. This paper identifies a new concept called Agentic Pressure, which…

Artificial Intelligence · Computer Science 2026-04-21 Hengle Jiang , Ke Tang