English
Related papers

Related papers: Theory of Code Space: Do Code Agents Understand So…

200 papers

Open source projects are adopting faster release cycles that reflect various changes. Therefore, comprehending the effects of these changes on software's architecture over the releases becomes necessary. However, it is challenging to keep…

Software Engineering · Computer Science 2020-12-23 A Eashaan Rao , Dheeraj Vagavolu , Sridhar Chimalakonda

Large language model (LLM) multi-agent coding systems typically fix agent capabilities at design time. We study an alternative setting, earned autonomy, in which a coding agent starts with zero pre-defined functions and incrementally builds…

Human-Computer Interaction · Computer Science 2026-03-31 Yinghao Wang , Cheng Wang

There is abundant observational data in the software engineering domain, whereas running large-scale controlled experiments is often practically impossible. Thus, most empirical studies can only report statistical correlations -- instead of…

Software Engineering · Computer Science 2024-10-03 Carlo A. Furia , Richard Torkar , Robert Feldt

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week…

Coding agents have received significant adoption in software development recently. Unlike traditional LLM-based code completion tools, coding agents work with autonomy (e.g., invoking external tools) and leave visible traces in software…

Software Engineering · Computer Science 2026-02-03 Andre Hora , Romain Robbes

The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…

Artificial Intelligence · Computer Science 2025-10-20 Ed Li , Junyu Ren , Xintian Pan , Cat Yan , Chuanhao Li , Dirk Bergemann , Zhuoran Yang

Computer systems are so complex, so they are usually designed and analyzed in terms of layers of abstraction. Complexity is still a challenge facing logical reasoning tools that are used to find software design flaws and implementation…

Software Engineering · Computer Science 2021-06-18 Ramy Shahin

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

Software Engineering · Computer Science 2025-12-29 Brian Bowers , Smita Khapre , Jugal Kalita

We consider the problem of the evolution of a code within a structured population of agents. The agents try to maximise their information about their environment by acquiring information from the outputs of other agents in the population. A…

Multiagent Systems · Computer Science 2015-05-18 Andres C. Burgos , Daniel Polani

While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent…

Computation and Language · Computer Science 2024-06-28 Huao Li , Yu Quan Chong , Simon Stepputtis , Joseph Campbell , Dana Hughes , Michael Lewis , Katia Sycara

In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real world is very diverse, and human behavior often changes in…

Machine Learning · Computer Science 2021-01-15 Paul Knott , Micah Carroll , Sam Devlin , Kamil Ciosek , Katja Hofmann , A. D. Dragan , Rohin Shah

Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric…

Machine Learning · Computer Science 2025-12-02 Florian Rottach , William Rudman , Bastian Rieck , Harrisen Scells , Carsten Eickhoff

AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…

Software Engineering · Computer Science 2026-04-24 Robert Feldt , Per Lenberg , Julian Frattini , Dhasarathy Parthasarathy

Rapid advances in Large Language Models (LLMs) create new opportunities by enabling efficient exploration of broad, complex design spaces. This is particularly valuable in computer architecture, where performance depends on…

Artificial Intelligence · Computer Science 2026-04-29 Alexander Blasberg , Vasilis Kypriotis , Dimitrios Skarlatos

Chain-of-thought (CoT) rationale enables language models to use additional task-related text for problem-solving, benefiting not only from detailed reasoning steps but also from the expanded computational space of longer inputs. Prior work…

Computation and Language · Computer Science 2025-09-30 Yoonna Jang , Kisu Yang , Isabelle Augenstein

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity:…

Software Engineering · Computer Science 2026-03-30 Mo Li , L. H. Xu , Qitai Tan , Ting Cao , Yunxin Liu

Computer-using agents have shown strong potential to boost human productivity and enable new application forms across platforms. While recent advances have led to usable applications, existing benchmarks fail to account for the internal…

Theory of Mind (ToM) refers to an agent's ability to model the internal states of others. Contributing to the debate whether large language models (LLMs) exhibit genuine ToM capabilities, our study investigates their ToM robustness using…

Computation and Language · Computer Science 2026-02-26 Christian Nickel , Laura Schrewe , Florian Mai , Lucie Flek

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a…

Software Engineering · Computer Science 2026-05-14 Hailin Zhong , Shengxin Zhu