Related papers: EET: Experience-Driven Early Termination for Cost-…
Autonomous agents based on Large Language Models (LLMs) have evolved from reactive assistants to systems capable of planning, executing actions via tools, and iterating over environment observations. However, they remain vulnerable to…
Generative artificial intelligence (GenAI) and agentic systems are moving software engineering from code-centric production toward intent-centric human-agent work in which natural language, repository context, tools, tests, and governance…
While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face significant limitations: Zero-RL suffers from inefficient exploration and mode degradation due…
The advances and availability of technologies involving Generative Artificial Intelligence (AI) are evolving clearly and explicitly, driving immediate changes in various work activities. Software Engineering (SE) is no exception and stands…
Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as…
Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to accurately reflect how developers interact with chat-based coding assistants in integrated…
Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness, the high computational cost of input tokens due to…
With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore…
As autonomous agentic systems scale across regulated critical infrastructures, the lack of mechanistic, hardware-rooted enforcement for high-frequency policy updates presents a fundamental safety gap. We introduce Ethical Hyper-Velocity…
The increasing complexity of software dependencies has led to the emergence of automated dependency management tools, such as Dependabot. However, these tools often overwhelm developers with a high volume of alerts and notifications,…
Pre-trained language models in the past years have shown exponential growth in model parameters and compute time. ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models (e.g. BERT) based on masked…
Prompt engineering is a crucial yet challenging task for optimizing the performance of large language models (LLMs) on customized tasks. This pioneering research introduces the Automatic Prompt Engineering Toolbox (APET), which enables…
Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practical adoption remains limited due to significant computational…
Reasoning large language models (LLMs) have demonstrated superior capacities in solving complicated problems by generating long chain-of-thoughts (CoT), but such a lengthy CoT incurs high inference costs. Previous methods on inference-stage…
While increasing research focuses on the emotional well-being of agile team members, a significant gap remains in emotion monitoring studies for Scrum Masters and meeting organizers, whose impact on team dynamics is crucial. This paper…
When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environment due to privacy or…
In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining. Our goal is to provide an easy-to-use BERT pretraining toolkit for the research community and industry. Thus, the pretraining of popular…
Modern search engine ranking pipelines are commonly based on large machine-learned ensembles of regression trees. We propose LEAR, a novel - learned - technique aimed to reduce the average number of trees traversed by documents to…
Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent advances in large language model (LLM)-based multi-agent…
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…