Tool use / function calling

ReAct: Synergizing Reasoning and Acting in Language Models

6 critique · 4 beaten on benchmarks

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

4 critique · 3 beaten on benchmarks

ToolACE: Winning the Points of LLM Function Calling

2 critique · 4 beaten on benchmarks

API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs

5 critique · 0 beaten on benchmarks

Gorilla: Large Language Model Connected with Massive APIs

3 critique · 1 beaten on benchmarks

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

2 critique · 1 beaten on benchmarks

2 critique · 1 beaten on benchmarks

Toolformer: Language Models Can Teach Themselves to Use Tools

2 critique · 1 beaten on benchmarks

APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets

3 critique · 0 beaten on benchmarks

xLAM: A Family of Large Action Models to Empower AI Agent Systems

0 critique · 2 beaten on benchmarks

ART: Automatic multi-step reasoning and tool-use for large language models

1 critique · 1 beaten on benchmarks

ExpeL: LLM Agents Are Experiential Learners

1 critique · 1 beaten on benchmarks