Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale
LLM-powered data agents are playing an increasingly important role in data-driven decision making. However, existing data agents struggle to generalize to unseen data environments and analytical workflows, especially in heterogeneous enterprise settings. This creates a growing need for synthesizing high-quality data agent trajectories that capture complex analytical workflows for given data environments. Such trajectories support two key downstream uses: they can serve as supervised finetuning (SFT) data that adapts data agent models to the target domain, and as in-context learning (ICL) demon
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%agent-tools →
- PossiblePossibly related (embedding) · 57%Yuqi-Zhou/LRAT →
- PossiblePossibly related (embedding) · 57%RimantasZ/contextspy →
- PossiblePossibly related (embedding) · 56%deepset-ai/haystack →
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “Demonstrating TOFFEE: A Learned System for Synthesizing Data” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 50%Build a unified semantic layer across datasets with multi-dataset Topics in Amazon Quick →
- PossiblePossibly related (embedding) · 48%Enrich your datasets with business context: Migrating from legacy Topics to semantic datasets in Amazon Quick →
- LinkedLinked via arxiv author · 85%Ziting Wang →
“Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale”