Related papers: Can Coding Agents Be General Agents?
The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…
Code completion has become a common practice for programmers during their daily programming activities. It aims at automatically predicting the next tokens or lines that the programmers tend to use. A good code completion tool can…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
We often assume that agent-to-agent interaction will mirror human conversation. However, agents operate fundamentally differently. What if they could develop communication patterns that are more efficient and better aligned with their…
The rapid proliferation of large language models (LLMs) and agentic AI systems has created an unprecedented abundance of automatically generated code, challenging the traditional software engineering paradigm centered on manual authorship.…
The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing…
Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise…
Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data,…
Current language models have demonstrated their capability to develop basic reasoning, but struggle in more complicated reasoning tasks that require a combination of atomic skills, such as math word problem requiring skills like arithmetic…
The main objective of this paper is to provide an optimized solution and algorithm for the execution of a workflow process by ensuring the data consistency, correctness, completeness among various tasks involved. The solution proposed…
The increasing adoption of foundation models as agents across diverse domains necessitates a robust evaluation framework. Current methods, such as LLM-as-a-Judge, focus only on final outputs, overlooking the step-by-step reasoning that…
When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, what…
As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long…
LLM-based agent systems are emerging as a new software paradigm and have been widely adopted across diverse domains such as medicine, robotics, and programming. However, maintaining these systems requires substantial effort, as they are…
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…
The proliferation of large language models (LLMs) has accelerated the adoption of agent-based workflows, where multiple autonomous agents reason, invoke functions, and collaborate to compose complex data pipelines. However, current…
The development of LLM-based autonomous agents for end-to-end software development represents a significant paradigm shift in software engineering. However, the scientific evaluation of these systems is hampered by significant challenges,…
The objective of this chapter is to propose some retrospective analysis of the evolution of programming abstractions, from {\em procedures}, {\em objects}, {\em actors}, {\em components}, {\em services}, up to {\em agents}, %have some…
Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…
Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general…