Related papers: BootstrapAgent: Distilling Repository Setup into R…
As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution…
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, current agentic systems are often retrieval-heavy but…
Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it…
Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial effort on environment setup, struggle to generate harnesses that respect intricate API…
Digital agents capable of automating complex computer tasks have attracted considerable attention due to their immense potential to enhance human-computer interaction. However, existing agent methods exhibit deficiencies in their…
The SZZ algorithm is the dominant technique for identifying bug-inducing commits and underpins many software engineering tasks, such as defect prediction and vulnerability analysis. Despite numerous variants, including recent LLM-based…
Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether such agents can…
Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tightly coupled to domain-specific data and formats. While…
Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong…
The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with…
Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been that commit messages describe human intent in natural language, and patches to code describe the…
Estimating causal effects from large experimental and observational data has become increasingly prevalent in both industry and research. The bootstrap is an intuitive and powerful technique used to construct standard errors and confidence…
In developed countries such as Australia, for recurring disasters (e.g. floods), there are dedicated document repositories of Disaster Management Plans (DISPLANs), and supporting doctrine and processes that are used to prepare organisations…
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.…
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting…
Training trustworthy agentic LLMs requires data that shows the grounded reasoning process, not just the final answer. Existing datasets fall short: question-answering data is outcome-only, chain-of-thought data is not tied to specific…
Mobile agents research is clearly aiming towards imposing agent based development as the next generation of tools for writing software. This paper comes with its own contribution to this global goal by introducing a novel unifying framework…
Generating the English transliteration of a name written in a foreign script is an important and challenging step in multilingual knowledge acquisition and information extraction. Existing approaches to transliteration generation require a…
Coding agents can generate web applications from natural-language descriptions, yet a recent benchmark study shows that generated applications fail to meet functional requirements in over 70% of cases. The core difficulty is that web…
To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a novel ``Extraction-Storage-Construction'' paradigm. The framework deconstructs…