Papers by Chun-Tin Wu
ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing benchmarks assess tools in isolation, overlooking challenges such as functional overlap and cross-server orchestration, which can lead to overly optimistic evaluations. |
| Approach: | They propose a five-level benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents within a hierarchical Model-Context Protocol (MCP) ecosystem. |
| Outcome: | The proposed framework evaluates end-to-end tool orchestration by agents in hierarchical Model-Context Protocol (MCP) environments. |