Unverified50% confidenceBenchmarkExact time
Anthropic's retrieval-based pre-filtering filters candidates by semantic similarity before injection, raising tool-use accuracy from 49% to 74% in scenarios with over a hundred tools.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedVariance-based contrastive optimization identifies problems in planning and tool invocation by contrasting samples with different performance levels.71% similarUnverifiedRetrieval-based matching strategies are able to identify the most skills (high recall), while generative strategies are more precise (high precision).68% similarUnverifiedOpenAI内部测试数据显示，经过思维链分解的提示词在结构化任务上的准确率平均提升约30%-40%67% similarUnverifiedMany of the current mainstream GUI agent evaluation benchmarks still use action matching or step reproduction methods for scoring67% similarUnverifiedThe fine-tuned search agent achieved measurable improvements in retrieval quality and reliability.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037733API
curl https://kongchang.com/api/v1/knowledge/claims/1037733MCP
get_claim(id=1037733)