PulseAugur
LIVE 00:03:02
research · [6 sources] ·
0
research

LLM agents explored for visualization, supply chain governance, and entity search

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 6 sources

Three new research papers explore different facets of Large Language Model (LLM) applications. One paper investigates interaction paradigms for LLM agents in scientific visualization, comparing domain-specific, computer-use, and general-purpose coding agents across various tasks and modalities. Another research paper proposes a governance framework for managing LLM updates in the software supply chain, focusing on production contracts, risk-based testing, and compatibility gates to address silent updates and behavioral drift. The third paper introduces an LLM-guided approach using attribute graphs for entity search and ranking in e-commerce, which improves precision and reduces token usage by reasoning over structured data. AI

Summary written by gemini-2.5-flash-lite from 6 sources. How we write summaries →

IMPACT These papers highlight advancements in LLM agent interaction, supply chain governance, and e-commerce search, suggesting improved efficiency and reliability in diverse AI applications.

RANK_REASON The cluster contains multiple academic papers submitted to arXiv, focusing on research into LLM applications and governance.

Read on arXiv cs.AI →

COVERAGE [6]

  1. arXiv cs.AI TIER_1 · Jackson Vonderhorst, Kuangshi Ai, Haichao Miao, Shusen Liu, Chaoli Wang ·

    Exploring Interaction Paradigms for LLM Agents in Scientific Visualization

    arXiv:2604.27996v1 Announce Type: new Abstract: This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three prima…

  2. arXiv cs.AI TIER_1 · Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li ·

    Test Before You Deploy: Governing Updates in the LLM Supply Chain

    arXiv:2604.27789v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates…

  3. arXiv cs.CL TIER_1 · Yilun Zhu, Nikhita Vedula, Shervin Malmasi ·

    From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking

    arXiv:2604.27410v1 Announce Type: cross Abstract: Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle…

  4. arXiv cs.AI TIER_1 · Chaoli Wang ·

    Exploring Interaction Paradigms for LLM Agents in Scientific Visualization

    This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three primary interaction paradigms, including domain-speci…

  5. arXiv cs.AI TIER_1 · Jingyue Li ·

    Test Before You Deploy: Governing Updates in the LLM Supply Chain

    Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can introduce behavioral drift, causing regressio…

  6. arXiv cs.CL TIER_1 · Shervin Malmasi ·

    From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking

    Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to capture nuanced context-specific attribute rel…

RELATED ENTITIES

RELATED TOPICS