-
-
workflow-induction-toolkit Public
A toolkit to induce interpretable workflows from raw computer-use activities.
-
agent-skill-induction Public
Agent Skill Induction: "Inducing Programmatic Skills for Agentic Tasks"
-
agent-workflow-memory Public
AWM: Agent Workflow Memory
-
trove Public
[ICML'24] TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
-
-
filco Public
[Preprint] Learning to Filter Context for Retrieval-Augmented Generaton
-
odex Public
[EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation
-
multilingual-conala Public
[EACL'23] MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages
-
nqt-retrieval Public
[SUKI'22] Table Retrieval May Not Necessitate Table-Specific Model Design
-
ChnEval Public
Intrinsic Knowledge Evaluation on Chinese Language Models