English
Related papers

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

200 papers

Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capacity for active, self-directed exploration remains…

As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or…

Software Engineering · Computer Science 2026-05-20 Priyansh Trivedi , Olivier Schmitt

AI coding assistants and autonomous agents are becoming integral to software development workflows, reshaping how code is produced, reviewed, and maintained. While recent research has focused mainly on the capabilities and impacts of…

Software Engineering · Computer Science 2026-05-07 Christoph Treude

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.…

Cryptography and Security · Computer Science 2025-10-03 Shoumik Saha , Jifan Chen , Sam Mayers , Sanjay Krishna Gouda , Zijian Wang , Varun Kumar

Agentic code assistants are a new generation of AI systems capable of performing end-to-end software engineering tasks. While these systems promise unprecedented productivity gains, their behavior and effectiveness depend heavily on…

Software Engineering · Computer Science 2026-05-26 Helio Victor F. Santos , Vitor Costa , Joao Eduardo Montandon , Marco Tulio Valente

Previous works from research and industry have proposed a spatial representation of code in a canvas, arguing that a navigational code space confers developers the freedom to organise elements according to their understanding. By allowing…

Software Engineering · Computer Science 2023-04-20 Abir Bouraffa , Gian-Luca Fuhrmann , Walid Maalej

We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely…

Human-Computer Interaction · Computer Science 2025-06-24 Nan Cao , Xiaoyu Qi , Chuer Chen , Xiaoke Yan

The exceptional capabilities of large language models (LLMs) have substantially accelerated the rapid rise and widespread adoption of agents. Recent studies have demonstrated that generating Python code to consolidate LLM-based agents'…

Software Engineering · Computer Science 2024-12-20 Ziyi Ni , Yifan Li , Daxiang Dong

Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good…

Software Engineering · Computer Science 2025-08-05 Ziyi Ni , Yifan Li , Ning Yang , Dou Shen , Pin Lv , Daxiang Dong

LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action…

Artificial Intelligence · Computer Science 2026-04-17 Myeongsoo Kim , Joe Hsu , Dingmin Wang , Shweta Garg , Varun Kumar , Murali Krishna Ramanathan

Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively.…

Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mind (ToM) tasks, where success requires reasoning from the user's perspective. However,…

Computation and Language · Computer Science 2026-05-28 Cheng Qian , Jiayu Liu , Heng Ji

Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…

Artificial Intelligence · Computer Science 2026-02-24 Tarakanath Paipuru

Computer-use agents(CUAs)are moving frombounded benchmarks toward real software environments, wherethey operate browsers, desktops, mobile applications, flesystems,terminals, and tool backends. In such settings, reliability isno longer…

Computation and Language · Computer Science 2026-05-11 Zejian Chen , Zhanyuan Liu , Chaozhuo Li , Mengxiang Han , Songyang Liu , Litian Zhang , Feng Gao , Yiming Hei , Xi Zhang

Large Language Models (LLMs) challenge conventional automated programming assessment because students can now produce functionally correct code without demonstrating corresponding understanding. This paper makes two contributions. First, it…

Software Engineering · Computer Science 2026-04-09 Eduard Frankford , Erik Cikalleshi , Ruth Breu

Software engineering faces a fundamental challenge: multi-agent AI systems fail in ways that defy explanation by traditional theories. While individual agents perform correctly, their interactions degrade entire ecosystems, revealing a gap…

Software Engineering · Computer Science 2026-04-23 Daniel Russo

LLM-based coding agents can localize bugs, generate patches, and run tests with diminishing human oversight, yet the scaffolding code that surrounds the language model (the control loop, tool definitions, state management, and context…

Software Engineering · Computer Science 2026-04-14 Benjamin Rombaut

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.…

Software Engineering · Computer Science 2026-04-06 Tural Mehtiyev , Wesley Assunção

Developing AI agents powered by large language models (LLMs) faces significant challenges in achieving true Turing completeness and adaptive, code-driven evolution. Current approaches often generate code independently of its runtime…

Software Engineering · Computer Science 2024-09-25 Ming Zhu , Yi Zhou

It is increasingly possible for real-world agents, such as software-based agents or human institutions, to view the internal programming of other such agents that they interact with. For instance, a company can read the bylaws of another…

Computer Science and Game Theory · Computer Science 2022-08-16 Andrew Critch , Michael Dennis , Stuart Russell
‹ Prev 1 2 3 10 Next ›