Unverified50% confidenceFactExact time
Tool F1 is a tool-call quality metric that combines precision and recall, and is more fine-grained than task success rate alone.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe researchers validated CITA on three tool-use benchmarks in combination with multiple different backbone LLMs, and the results show consistent improvements on both Tool F1 and task success rate metrics.74% similarUnverified工具动态召回机制先从大规模工具库中通过向量检索筛选最相关的候选工具，再交由模型最终决策，以缓解工具描述质量参差带来的准确率衰减73% similarUnverifiedTesting tool-calling accuracy requires attention to three levels: tool selection accuracy, parameter extraction accuracy, and tool chain orchestration rationality, of which parameter extraction is often the most error-prone.70% similarUnverifiedEvaluation metrics suitable for the systematic review screening scenario include recall, precision, F1 score, and Work Saved over Sampling (WSS).68% similarUnverified工具描述质量直接决定模型是否选对工具，模型在所有已注册工具的描述文本中进行语义匹配67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/975636API
curl https://kongchang.com/api/v1/knowledge/claims/975636MCP
get_claim(id=975636)