LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
This provides a more realistic evaluation framework for LLM agents in assistant applications, though it is incremental as it builds on existing benchmarking efforts.
The authors tackled the gap between existing LLM agent benchmarks and real-world assistant tasks by introducing LiveClawBench, a benchmark based on a Triple-Axis Complexity Framework, which evaluates agents on tasks with compositional difficulty derived from real usage cases.
LLM-based agents are increasingly expected to handle real-world assistant tasks, yet existing benchmarks typically evaluate them under isolated sources of difficulty, such as a single environment or fully specified instructions. This leaves a substantial gap between current evaluation settings and the compositional challenges that arise in practical deployment. To address this gap, we introduce LiveClawBench, a benchmark to evaluate LLM agents on real-world assistant tasks. Based on an analysis of various real OpenClaw usage cases, we derive a Triple-Axis Complexity Framework that characterizes task difficulty along three dimensions: Environment Complexity, Cognitive Demand, and Runtime Adaptability. Guided by this framework, we construct a pilot benchmark with explicit complexity-factor annotations, covering real-world assistant tasks with compositional difficulty. Together, the framework and benchmark provide a principled foundation for evaluating LLM agents in realistic assistant settings, and establish a basis for future expansion across task domains and complexity axes. We are continuing to enrich our case collections to achieve more comprehensive domain and complexity coverage. The project page is at https://github.com/Mosi-AI/LiveClawBench.