Related papers: Stage-Audit: Auditable Source-Frontier Discovery f…
Emerging personal AI agents are moving toward persistent, multi-source memory. This creates an evaluation problem: systems must decide how to use conflicting or incomplete evidence; they cannot just retrieve facts from one clean history.…
The rapid growth of blockchain technology has driven the widespread adoption of smart contracts. However, their inherent vulnerabilities have led to significant financial losses. Traditional auditing methods, while essential, struggle to…
As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a…
This paper argues that large ML conferences should allocate marginal review capacity primarily to papers near the acceptance boundary, rather than spreading extra reviews via random or affinity-driven heuristics. We propose using LLM-based…
Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluation approaches rely on rule-based metrics that fail to capture semantic equivalence of table…
LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on…
Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning. As these systems scale, the robustness of this retrieval stage is…
Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generations, failing to capture how an agent reasons through iterative interaction. To address…
The emergence of Large Language Models (LLMs) has opened new opportunities to automate software engineering activities that traditionally require substantial manual effort. Among these, class diagram generation represents a critical yet…
We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools…
Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code,…
When does an LLM controller outperform rule-based traversal for knowledge graph exploration? We study this question through RLM-on-KG, a retrieval system that treats an LLM as an autonomous navigator over an RDF-encoded mention graph for…
Author Name Disambiguation (AND) is a long-standing challenge in bibliometrics and scientometrics, as name ambiguity undermines the accuracy of bibliographic databases and the reliability of research evaluation. This study addresses the…
When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating agreement as the finish line. We show this is unnecessarily lossy: an LLM aggregator…
Low-level approach is a novel way to detect source code plagiarism. Such approach is proven to be effective when compared to baseline approach (i.e., an approach which relies on source code token subsequence matching) in controlled…
Recent advancements in table-based reasoning have expanded beyond factoid-level QA to address insight-level tasks, where systems should synthesize implicit knowledge in the table to provide explainable analyses. Although effective, existing…
Large language models (LLMs) are increasingly adopted for automating survey paper generation \cite{wang2406autosurvey, liang2025surveyx, yan2025surveyforge,su2025benchmarking,wen2025interactivesurvey}. Existing approaches typically extract…
LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool…
The rapid adoption of large language models (LLMs) in scientific writing raises serious concerns regarding authorship integrity and the reliability of scholarly publications. Existing detection approaches mainly rely on document-level…
Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…