Related papers: CodeCompass: Navigating the Navigation Paradox in …
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…
Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However, such fixed schemes often suffer from two key limitations.…
Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and limited sensing, challenges that classical controllers struggle to address. This demands…
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…
The graph-navigability problem concerns how one can find as short paths as possible between a pair of vertices, given an incomplete picture of a graph. We study the navigability of graphs where the vertices are tagged by a number (between 1…
In recent years, the rapid increase in academic publications across various fields has posed severe challenges for academic paper analysis: scientists struggle to timely and comprehensively track the latest research findings and…
Programming tutorials are often created to demonstrate programming tasks with code examples. However, our study of Stack Overflow questions reveals the low utilization of high-quality programming tutorials, which is caused task description…
Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework…
Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data…
Knowledge graphs provide structured context for multi-hop question answering, but deployed systems must balance answer accuracy with strict latency and cost targets while preserving provenance. Static k-hop expansions and "think-longer"…
Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems…
In the graph exploration problem, a team of mobile computational entities, called agents, arbitrarily positioned at some nodes of a graph, must cooperate so that each node is eventually visited by at least one agent. In the literature, the…
Agentic exploration, letting LLM-powered agents branch, backtrack, and search across many execution paths, demands systems support well beyond today's pass-at-k resets. Our benchmark of six snapshot/restore mechanisms shows that generic…
Responding to Hodel et al.'s (2024) call for a formal definition of task relatedness in re-arc, we present the first 9-category taxonomy of all 400 tasks, validated at 97.5% accuracy via rule-based code analysis. We prove the taxonomy's…
Collaborative perception leverages data exchange among multiple agents to enhance overall perception capabilities. However, heterogeneity across agents introduces domain gaps that hinder collaboration, and this is further exacerbated by an…
LLM agents excel when environments are mostly static and the needed information fits in a model's context window, but they often fail in open-ended investigations where explanations must be constructed by iteratively mining evidence from…
With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and…
The dominant paradigm for training Large Vision-Language Models (LVLMs) in navigation relies on imitating expert trajectories. This approach reduces the complex navigation task to a sequence-to-sequence replication of a single correct path,…
In real-world data science and enterprise decision-making, critical information is often fragmented across directly queryable structured sources (e.g., SQL, CSV) and "zombie data" locked in unstructured visual documents (e.g., scanned…