Related papers: From Helpful to Trustworthy: LLM Agents for Pair P…

In the software industry, the drive to add new features often overshadows the need to improve existing code. Large Language Models (LLMs) offer a new approach to improving codebases at an unprecedented scale through AI-assisted refactoring.…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Software agents, both human and computational, do not exist in isolation and often need to collaborate or coordinate with others to achieve their goals. In human society, social mechanisms such as norms ensure efficient functioning, and…

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide…

Large Language Models (LLMs) are frequently discussed in academia and the general public as support tools for virtually any use case that relies on the production of text, including software engineering. Currently there is much debate, but…

We propose Love First, Know Later: a paradigm shift in computational matching that simulates interactions first, then assesses compatibility. Instead of comparing static profiles, our framework leverages LLMs as text world engines that…

Multi-agent collaboration among models has shown promise in reasoning tasks but is underexplored in long-form generation tasks like summarization and question-answering. We extend multi-agent multi-model reasoning to generation,…

LLMs are transforming software engineering by accelerating development, reducing complexity, and cutting costs. When fully integrated into the software lifecycle they will drive design, development and deployment while facilitating early…

The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are software toolkits and libraries that provide standardized components, abstractions,…

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans…

This paper introduces UniTranslator, a visionary framework that re-imagines code translation as a collaborative endeavor among multiple, compact LLMs. By orchestrating the interaction of specialized agents, each focused on different aspects…

The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract reasoning about program properties that is challenging for…

Large language models (LLMs) can potentially help with verification using proof assistants by automating proofs. However, it is unclear how effective LLMs are in this task. In this paper, we perform a case study based on two mature Rocq…

Large Language Models (LLMs) are increasingly being integrated into software development processes, with the potential to transform team workflows and productivity. This paper investigates how LLMs affect team collaboration throughout the…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

Incorporating LLM into cybersecurity operations, a typical real-world high-stakes task, is critical but non-trivial in practice. Using cybersecurity as the study context, we conduct a three-step mix-method study to incorporate LLM into the…

The rise of large language models (LLMs) has introduced transformative potential in automated code generation, addressing a wide range of software engineering challenges. However, empirical evaluation of LLM-based code generation lacks…

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…

Large Language Model (LLM) Agents leverage the advanced reasoning capabilities of LLMs in real-world applications. To interface with an environment, these agents often rely on tools, such as web search or database APIs. As the agent…

As the strength of Large Language Models (LLMs) has grown over recent years, so too has interest in their use as the underlying models for autonomous agents. Although LLMs demonstrate emergent abilities and broad expertise across natural…