Related papers: DocSync: Agentic Documentation Maintenance via Cri…
Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence, yet evaluating RAG systems in specialized, safety-critical domains remains a significant challenge. Existing…
Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…
Recent autonomous AI agents such as Codex, and Claude Code have made it increasingly practical for users to delegate complex tasks, including writing emails, executing code, issuing shell commands, and carrying out multi-step plans.…
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles with the inherent need of this domain for document-based…
We present the Code Documentation and Analysis Tool (CoDAT). CoDAT is a tool designed to maintain consistency between the various levels of code documentation, e.g. if a line in a code sketch is changed, the comment that documents the…
Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…
Large Language Models (LLMs) suffer from a critical limitation: their knowledge is static and quickly becomes outdated. Retraining these massive models is computationally prohibitive, while existing knowledge editing techniques can be slow…
Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…
Many decentralized decision problems require multiple parties to coordinate on shared decisions while keeping objectives, constraints, and data private. Large language models (LLMs) offer a promising way to lower the barrier to…
The rapid evolution of neural architectures - from multilayer perceptrons to large-scale Transformer-based models - has enabled language models (LLMs) to exhibit emergent agentic behaviours when equipped with memory, planning, and external…
The emergence of large language models has enabled sophisticated multi-agent systems, yet coordinating their reasoning capabilities through prompt engineering remains challenging. We present a theoretically-grounded framework for dynamic…
Information retrieval is a cornerstone of modern knowledge acquisition, enabling billions of queries each day across diverse domains. However, traditional keyword-based search engines are increasingly inadequate for handling complex,…
Neuroscience data are highly fragmented across labs, formats, and experimental paradigms, and reuse often requires substantial manual effort. A persistent roadblock to data reuse and integration is the need to decipher bespoke and diverse…
Agentic systems have been widely studied to automate software engineering jobs such as bug fixing. As these systems increasingly tackle complex tasks, understanding where and why they fail becomes essential for iterative refinement and…
Recent advances in LLM-based Text-to-SQL have achieved remarkable gains on public benchmarks such as BIRD and Spider. Yet, these systems struggle to scale in realistic enterprise settings with large, complex schemas, diverse SQL dialects,…
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We…
Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that fixes the source code based on test failures at scale…
Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the multi-scale credit assignment…
With the continuous growth in the scale and complexity of software systems, defect remediation has become increasingly difficult and costly. Automated defect prediction tools can proactively identify software changes prone to defects within…
Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…