ToolBench

ToolBench is a dataset used to evaluate the performance of agents on various programming tasks, focusing on aspects such as correctness and error handling.

Papers using ToolBench (10)

Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning2025 · 14 citesCoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval2026Adarubric: Task-adaptive Rubrics For LLM Agent Evaluation2026How Many Tools Should an LLM Agent See? A Chance-Corrected Answer2026Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use2026Agenther: Hindsight Experience Replay For LLM Agent Trajectory Relabeling2026Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents2026Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning2026NaviAgent: Graph-Driven Bilevel Planning for Scalable Tool Orchestration2025Toolplanner: A Tool Augmented LLM For Multi Granularity Instructions With Path Planning And Feedback2024 · 4 cites