LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
Data Interpreter : An LLM Agent For Data Science
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
CellDX AI Autopilot lets users train pathology classifiers via AI agent skills on a large pre-extracted whole-slide image dataset with automated hyperparameter tuning that claims over 30x cost reduction.
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
ProfiliTable is a profiling-driven multi-agent system that builds semantic context through exploration and closed-loop refinement to produce more reliable tabular data transformations than prior LLM approaches.
citing papers explorer
-
Figures as Interfaces: Toward LLM-Native Artifacts for Scientific Discovery
LLM-native figures embed provenance and enable direct LLM interaction with scientific visualizations to accelerate discovery and improve reproducibility.
-
CellDX AI Autopilot: Agent-Guided Training and Deployment of Pathology Classifiers
CellDX AI Autopilot lets users train pathology classifiers via AI agent skills on a large pre-extracted whole-slide image dataset with automated hyperparameter tuning that claims over 30x cost reduction.
-
AgentGA: Evolving Code Solutions in Agent-Seed Space
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows
ProfiliTable is a profiling-driven multi-agent system that builds semantic context through exploration and closed-loop refinement to produce more reliable tabular data transformations than prior LLM approaches.